Loading pre-trained spanBERT from ./pretrained_spanbert ____ Parameters: Client key = XXXXXX Engine key = XXXXXX Gemini key = XXXXXX Method = spanbert Relation = Work_For Threshold = 0.7 Query = sundar pichai google # of Tuples = 40 Loading necessary libraries; This should take a minute or so ...) =========== Iteration: 0 - Query: sundar pichai google =========== URL ( 1 / 10): https://en.wikipedia.org/wiki/Sundar_Pichai Fetching text from url ... Trimming webpage content from 34144 to 10000 characters Webpage length (num characters): 10000 Annotating the webpage using spacy... Extracted 105 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 105 sentences === Extracted Relation === Input tokens: ['MBA)OccupationBusinessmanTitleCEO', 'of', 'Alphabet', 'and', 'GoogleBoard', 'member', 'ofAlphabet', 'Inc.[1]Magic', 'Leap', '('] Output Confidence: 0.99695766 ; Subject: ofAlphabet Inc.[1]Magic ; Object: Alphabet ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['MBA)OccupationBusinessmanTitleCEO', 'of', 'Alphabet', 'and', 'GoogleBoard', 'member', 'ofAlphabet', 'Inc.[1]Magic', 'Leap', '(', '2014–2018)[2]SpouseAnjali', 'PichaiChildren2Awards', 'Padma', 'Bhushan', '('] Output Confidence: 0.5595584 ; Subject: Padma Bhushan ; Object: Alphabet ; Confidence is lower than threshold confidence. Ignoring this. ========== === Extracted Relation === Input tokens: ['MBA)OccupationBusinessmanTitleCEO', 'of', 'Alphabet', 'and', 'GoogleBoard', 'member', 'ofAlphabet', 'Inc.[1]Magic', 'Leap', '(', '2014–2018)[2]SpouseAnjali', 'PichaiChildren2Awards', 'Padma', 'Bhushan', '(', '2022', ')', 'Sundar', 'Pichai', "'s", 'voice', 'Sundar', 'Pichai', 'on', 'being', 'CEO', 'of', 'GoogleRecorded', 'December', '11', ','] Output Confidence: 0.5595584 ; Subject: Sundar Pichai's ; Object: Alphabet ; Confidence is lower than threshold confidence. Ignoring this. ========== === Extracted Relation === Input tokens: ['MBA)OccupationBusinessmanTitleCEO', 'of', 'Alphabet', 'and', 'GoogleBoard', 'member', 'ofAlphabet', 'Inc.[1]Magic', 'Leap', '(', '2014–2018)[2]SpouseAnjali', 'PichaiChildren2Awards', 'Padma', 'Bhushan', '(', '2022', ')', 'Sundar', 'Pichai', "'s", 'voice', 'Sundar', 'Pichai', 'on', 'being', 'CEO', 'of', 'GoogleRecorded', 'December', '11', ','] Output Confidence: 0.5595584 ; Subject: Sundar Pichai ; Object: Alphabet ; Confidence is lower than threshold confidence. Ignoring this. ========== === Extracted Relation === Input tokens: ['MBA)OccupationBusinessmanTitleCEO', 'of', 'Alphabet', 'and', 'GoogleBoard', 'member', 'ofAlphabet', 'Inc.[1]Magic', 'Leap', '('] Output Confidence: 0.9035453 ; Subject: ofAlphabet Inc.[1]Magic ; Object: GoogleBoard ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['better', 'known', 'as', 'Sundar', 'Pichai', '(', '/ˈsʊndɑːr', 'pɪˈtʃaɪ/', ')', ',', 'is', 'an', 'Indian', '-', 'born', 'American', 'business', 'executive.[6][7', ']'] Output Confidence: 0.99652606 ; Subject: Sundar Pichai ; Object: executive.[6][7 ; Adding to set of extracted relations ========== Processed 10 / 105 sentences Processed 15 / 105 sentences === Extracted Relation === Input tokens: ['Pichai', 'added', 'Android', 'to', 'the', 'list', 'of', 'Google', 'products', 'that', 'he', 'oversaw', '.'] Output Confidence: 0.7732052 ; Subject: Pichai ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'was', 'selected', 'to', 'become', 'the', 'next', 'CEO', 'of', 'Google', 'on', 'August', '10', ','] Output Confidence: 0.9970755 ; Subject: Pichai ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'was', 'selected', 'to', 'become', 'the', 'next', 'CEO', 'of', 'Google', 'on', 'August', '10', ',', '2015', ',', 'after', 'previously', 'being', 'appointed', 'Product', 'Chief', 'by', 'the', 'then', 'CEO', 'Larry', 'Page', '.'] Output Confidence: 0.9970794 ; Subject: Larry Page ; Object: Google ; Adding to set of extracted relations ========== Processed 20 / 105 sentences === Extracted Relation === Input tokens: ['Regunatha', 'Pichai', ',', 'was', 'an', 'electrical', 'engineer', 'at', 'GEC', ','] Output Confidence: 0.9442318 ; Subject: Regunatha Pichai ; Object: GEC ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Spain', 'Pichai', 'worked', 'in', 'engineering', 'and', 'product', 'management', 'at', 'Applied', 'Materials', 'and', 'in', 'management', 'consulting', 'at', 'McKinsey', '&'] Output Confidence: 0.9960235 ; Subject: Pichai ; Object: Applied Materials ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Spain', 'Pichai', 'worked', 'in', 'engineering', 'and', 'product', 'management', 'at', 'Applied', 'Materials', 'and', 'in', 'management', 'consulting', 'at', 'McKinsey', '&', 'Company.[26', ']'] Output Confidence: 0.9950949 ; Subject: Pichai ; Object: McKinsey & Company.[26 ; Adding to set of extracted relations ========== Processed 25 / 105 sentences === Extracted Relation === Input tokens: ['Pichai', 'added', 'Android', 'to', 'the', 'list', 'of', 'Google', 'products', 'that', 'he', 'oversaw', '.'] Output Confidence: 0.7732052 ; Subject: Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 30 / 105 sentences === Extracted Relation === Input tokens: ['Android', 'was', 'formerly', 'managed', 'by', 'Andy', 'Rubin,[32', ']', 'who', 'was', 'a', 'director', 'of', 'Jive', 'Software', 'from', 'April', '2011', 'to', 'July', '30', ','] Output Confidence: 0.9963161 ; Subject: Andy Rubin,[32 ; Object: Jive Software ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'was', 'selected', 'to', 'become', 'the', 'next', 'CEO', 'of', 'Google', 'on', 'August', '10', ','] Output Confidence: 0.9970755 ; Subject: Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== === Extracted Relation === Input tokens: ['Pichai', 'was', 'selected', 'to', 'become', 'the', 'next', 'CEO', 'of', 'Google', 'on', 'August', '10', ',', '2015,[36', ']', 'after', 'previously', 'being', 'appointed', 'Product', 'Chief', 'by', 'CEO', ',', 'Larry', 'Page', '.'] Output Confidence: 0.99725914 ; Subject: Larry Page ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'had', 'been', 'suggested', 'as', 'a', 'contender', 'for', 'Microsoft', "'s", 'CEO', 'in', '2014', ',', 'a', 'position', 'that', 'was', 'eventually', 'given', 'to', 'Satya', 'Nadella.[38][39', ']'] Output Confidence: 0.8829768 ; Subject: Satya Nadella.[38][39 ; Object: Microsoft ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'drew', 'publicity', 'for', 'firing', 'a', 'Google', 'employee', 'who', 'wrote', 'a', 'ten', '-'] Output Confidence: 0.5488792 ; Subject: Pichai ; Object: Google ; Confidence is lower than threshold confidence. Ignoring this. ========== Processed 35 / 105 sentences === Extracted Relation === Input tokens: ['Pichai', 'was', 'a', 'speaker', 'at', 'the', 'World', 'Internet', 'Conference', 'in', 'China', ','] Output Confidence: 0.9957271 ; Subject: Pichai ; Object: the World Internet Conference ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Pichai', 'became', 'the', 'CEO', 'of', 'Alphabet', 'Inc.[47][48', ']'] Output Confidence: 0.9973 ; Subject: Pichai ; Object: Alphabet ; Adding to set of extracted relations ========== Processed 40 / 105 sentences === Extracted Relation === Input tokens: ['to', 'subpoena', 'Pichai', ',', 'along', 'with', 'Facebook', '(', 'today', 'Meta', ')', 'CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.78901273 ; Subject: Pichai ; Object: Twitter ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['along', 'with', 'Facebook', '(', 'today', 'Meta', ')', 'CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.9186752 ; Subject: Mark Zuckerberg ; Object: Facebook ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['along', 'with', 'Facebook', '(', 'today', 'Meta', ')', 'CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.98028326 ; Subject: Jack Dorsey ; Object: Facebook ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['today', 'Meta', ')', 'CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.72635496 ; Subject: Mark Zuckerberg ; Object: Meta ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['today', 'Meta', ')', 'CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.992446 ; Subject: Jack Dorsey ; Object: Meta ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.9291089 ; Subject: Mark Zuckerberg ; Object: Twitter ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['CEO', 'Mark', 'Zuckerberg', 'and', 'then', 'Twitter', 'CEO', 'Jack', 'Dorsey', ','] Output Confidence: 0.9955069 ; Subject: Jack Dorsey ; Object: Twitter ; Adding to set of extracted relations ========== Processed 45 / 105 sentences Processed 50 / 105 sentences Processed 55 / 105 sentences Processed 60 / 105 sentences Processed 65 / 105 sentences Processed 70 / 105 sentences === Extracted Relation === Input tokens: ['in', 'full', 'Pichai', 'Sundararajan', ',', '(', 'born', 'June', '10', ',', '1972', ',', 'Madras', '[', 'now', 'Chennai', ']', ',', 'Tamil', 'Nadu', ',', 'India', ')', ',', 'Indian', '-', 'born', 'American', 'executive', 'who', 'was', 'CEO', 'of', 'both', 'Google', ',', 'Inc.', '('] Output Confidence: 0.99645483 ; Subject: Pichai Sundararajan ; Object: Google, Inc. ; Adding to set of extracted relations ========== Processed 75 / 105 sentences Processed 80 / 105 sentences Processed 85 / 105 sentences === Extracted Relation === Input tokens: ['"', 'Google', 'CEO', 'Sundar', 'Pichai', 'Appointed', 'To', 'Alphabet', 'Board', 'Of', 'Directors', '"'] Output Confidence: 0.989757 ; Subject: Sundar Pichai ; Object: Google ; Adding to set of extracted relations ========== Processed 90 / 105 sentences Processed 95 / 105 sentences Processed 100 / 105 sentences Processed 105 / 105 sentences Extracted annotations for 16 out of total 105 sentences Relations extracted from this website: 23 (Overall: 29) URL ( 2 / 10): https://blog.google/authors/sundar-pichai/ Fetching text from url ... Webpage length (num characters): 3680 Annotating the webpage using spacy... Extracted 24 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 24 sentences Processed 10 / 24 sentences === Extracted Relation === Input tokens: ['CEO', 'Ruth', 'Porat', ',', 'SVP', 'and', 'CFO', 'Kent', 'Walker', ','] Output Confidence: 0.8444577 ; Subject: Ruth Porat ; Object: SVP ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['CEO', 'Ruth', 'Porat', ',', 'SVP', 'and', 'CFO', 'Kent', 'Walker', ','] Output Confidence: 0.8444577 ; Subject: Ruth Porat ; Object: SVP ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 15 / 24 sentences === Extracted Relation === Input tokens: ['CEO', 'Ruth', 'Porat', ',', 'SVP', 'and', 'CFO', 'Kent', 'Walker', ','] Output Confidence: 0.8444577 ; Subject: Ruth Porat ; Object: SVP ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 20 / 24 sentences Extracted annotations for 3 out of total 24 sentences Relations extracted from this website: 1 (Overall: 3) URL ( 3 / 10): https://www.businessinsider.com/calls-for-google-ceo-sundar-pichai-alphabet-step-down-ai-2024-3 Fetching text from url ... Webpage length (num characters): 8899 Annotating the webpage using spacy... Extracted 83 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 83 sentences Processed 10 / 83 sentences Processed 15 / 83 sentences === Extracted Relation === Input tokens: ['Log', 'in', 'Subscribe', 'Tech', 'There', 'are', 'growing', 'calls', 'for', 'Google', 'CEO', 'Sundar', 'Pichai', 'to', 'step', 'down', 'Hugh', 'Langley', '2024', '-'] Output Confidence: 0.99378896 ; Subject: Sundar Pichai ; Object: Google ; Adding to set of extracted relations ========== Processed 20 / 83 sentences Processed 25 / 83 sentences Processed 30 / 83 sentences Processed 35 / 83 sentences Processed 40 / 83 sentences Processed 45 / 83 sentences Processed 50 / 83 sentences Processed 55 / 83 sentences === Extracted Relation === Input tokens: ['Related', 'stories', 'Pichai', ',', 'who', 'was', 'appointed', 'CEO', 'of', 'Google', 'in', '2015', 'and', 'Alphabet', 'in', '2019', ','] Output Confidence: 0.99270064 ; Subject: Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== === Extracted Relation === Input tokens: ['Aravind', 'Srinivas', '—', 'a', 'founder', 'and', 'CEO', 'of', 'Perplexity', ','] Output Confidence: 0.9954632 ; Subject: Aravind Srinivas ; Object: Perplexity ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Aravind', 'Srinivas', '—', 'a', 'founder', 'and', 'CEO', 'of', 'Perplexity', ',', 'a', 'former', 'OpenAI', 'researcher', ','] Output Confidence: 0.99497056 ; Subject: Aravind Srinivas ; Object: OpenAI ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Aravind', 'Srinivas', '—', 'a', 'founder', 'and', 'CEO', 'of', 'Perplexity', ',', 'a', 'former', 'OpenAI', 'researcher', ',', 'and', 'a', 'former', 'Google', 'and', 'DeepMind', 'intern', '—'] Output Confidence: 0.9919569 ; Subject: Aravind Srinivas ; Object: Google ; Adding to set of extracted relations ========== Processed 60 / 83 sentences === Extracted Relation === Input tokens: ['Srinivas', 'wrote', 'on', 'X.Marissa', 'has', 'viewsEven', 'Marissa', 'Mayer', ',', 'who', 'was', 'Google', "'s", '20th', 'employee', 'ever', 'and', 'worked', 'there', 'for', '13', 'years', ','] Output Confidence: 0.9935331 ; Subject: Srinivas ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Srinivas', 'wrote', 'on', 'X.Marissa', 'has', 'viewsEven', 'Marissa', 'Mayer', ',', 'who', 'was', 'Google', "'s", '20th', 'employee', 'ever', 'and', 'worked', 'there', 'for', '13', 'years', ','] Output Confidence: 0.93322414 ; Subject: X.Marissa ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Srinivas', 'wrote', 'on', 'X.Marissa', 'has', 'viewsEven', 'Marissa', 'Mayer', ',', 'who', 'was', 'Google', "'s", '20th', 'employee', 'ever', 'and', 'worked', 'there', 'for', '13', 'years', ','] Output Confidence: 0.97429043 ; Subject: Marissa Mayer ; Object: Google ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Responding', 'to', 'a', 'tweet', 'by', 'Othman', 'Laraki', ',', 'the', 'CEO', 'of', 'Color', 'Health', ','] Output Confidence: 0.99530756 ; Subject: Othman Laraki ; Object: Color Health ; Adding to set of extracted relations ========== Processed 65 / 83 sentences Processed 70 / 83 sentences === Extracted Relation === Input tokens: ['Axel', 'Springer', ',', 'Business', 'Insider', "'s", 'parent', 'company', ',', 'joined', '31', 'other', 'media', 'groups', 'and', 'filed', 'a', '$', '2.3', 'billion', 'suit', 'against', 'Google', 'in', 'Dutch', 'court', ','] Output Confidence: 0.5767071 ; Subject: Axel Springer ; Object: Google ; Confidence is lower than threshold confidence. Ignoring this. ========== Processed 75 / 83 sentences Processed 80 / 83 sentences Extracted annotations for 6 out of total 83 sentences Relations extracted from this website: 8 (Overall: 10) URL ( 4 / 10): https://www.instagram.com/sundarpichai/?hl=en Fetching text from url ... Webpage length (num characters): 19 Annotating the webpage using spacy... Extracted 1 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Extracted annotations for 0 out of total 1 sentences Relations extracted from this website: 0 (Overall: 0) URL ( 5 / 10): https://twitter.com/sundarpichai?lang=en Fetching text from url ... Webpage length (num characters): 257 Annotating the webpage using spacy... Extracted 4 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Extracted annotations for 0 out of total 4 sentences Relations extracted from this website: 0 (Overall: 0) URL ( 6 / 10): https://www.semafor.com/article/02/27/2024/google-ceo-sundar-pichai-calls-ai-tools-responses-completely-unacceptable Fetching text from url ... Webpage length (num characters): 6110 Annotating the webpage using spacy... Extracted 58 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... === Extracted Relation === Input tokens: ['Google', 'CEO', 'Sundar', 'Pichai', 'calls', 'AI', 'toolâ\x80\x99s', 'responses', 'â\x80\x98completely', 'unacceptableâ\x80\x99', '|', 'SemaforEventsNewslettersHomepoliticsbusinesstechnologynet', 'zeroafricasecuritymediaVideo'] Output Confidence: 0.9888908 ; Subject: Sundar Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 5 / 58 sentences Processed 10 / 58 sentences === Extracted Relation === Input tokens: ['viewThe', 'ScoopGoogle', 'CEO', 'Sundar', 'Pichai', 'addressed', 'the', 'companyâ\x80\x99s', 'Gemini', 'controversy', 'Tuesday', 'evening', ','] Output Confidence: 0.8257356 ; Subject: Sundar Pichai ; Object: ScoopGoogle ; Adding to set of extracted relations ========== Processed 15 / 58 sentences Processed 20 / 58 sentences Processed 25 / 58 sentences Processed 30 / 58 sentences Processed 35 / 58 sentences Processed 40 / 58 sentences Processed 45 / 58 sentences Processed 50 / 58 sentences Processed 55 / 58 sentences Extracted annotations for 2 out of total 58 sentences Relations extracted from this website: 1 (Overall: 2) URL ( 7 / 10): https://www.britannica.com/biography/Sundar-Pichai Fetching text from url ... Webpage length (num characters): 7245 Annotating the webpage using spacy... Extracted 51 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 51 sentences Processed 10 / 51 sentences Processed 15 / 51 sentences Processed 20 / 51 sentences Processed 25 / 51 sentences === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.995001 ; Subject: Sundararajan Pichai ; Object: Encyclopædia Britannica ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.9966107 ; Subject: Sundararajan Pichai ; Object: Britannica Book of the Year ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.992464 ; Subject: Melinda C. Shepherd ; Object: Encyclopædia Britannica ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.99550307 ; Subject: Melinda C. Shepherd ; Object: Britannica Book of the Year ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.9942706 ; Subject: Melinda Shepherd ; Object: Encyclopædia Britannica ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Sundararajan', 'Pichai', 'Written', 'by', 'Melinda', 'C.', 'Shepherd', 'Melinda', 'Shepherd', 'became', 'an', 'editor', 'at', 'Encyclopædia', 'Britannica', 'in', '1988', 'and', 'served', 'as', 'a', 'senior', 'editor', 'of', 'Britannica', 'Book', 'of', 'the', 'Year', 'from', '2004', 'to', '2016', '.'] Output Confidence: 0.9962886 ; Subject: Melinda Shepherd ; Object: Britannica Book of the Year ; Adding to set of extracted relations ========== Processed 30 / 51 sentences Processed 35 / 51 sentences === Extracted Relation === Input tokens: ['Google', 'CEO', 'Pichai', 'says', 'Gemini', "'s", 'AI', 'image', 'results', '"'] Output Confidence: 0.99509877 ; Subject: Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== === Extracted Relation === Input tokens: ['Google', 'CEO', 'Sundar', 'Pichai', 'says', 'Show', 'More', 'Show'] Output Confidence: 0.9958059 ; Subject: Sundar Pichai ; Object: Google ; Adding to set of extracted relations ========== Processed 40 / 51 sentences Processed 45 / 51 sentences === Extracted Relation === Input tokens: ['Therefore', ',', 'when', 'Google', 'cofounders', 'Larry', 'Page', 'and', 'Sergey', 'Brin', 'announced', 'the', 'creation', 'of', 'Alphabet', 'Inc.', ','] Output Confidence: 0.9840459 ; Subject: Larry Page ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 50 / 51 sentences === Extracted Relation === Input tokens: ['In', 'December', '2019', 'he', 'also', 'was', 'named', 'CEO', 'of', 'Alphabet', ',', 'replacing', 'Page', ','] Output Confidence: 0.9968208 ; Subject: Page ; Object: Alphabet ; Adding to set of extracted relations ========== Extracted annotations for 5 out of total 51 sentences Relations extracted from this website: 8 (Overall: 10) URL ( 8 / 10): https://www.businessroundtable.org/about-us/members/sundar-pichai-ceo-alphabet-inc Fetching text from url ... Webpage length (num characters): 4571 Annotating the webpage using spacy... Extracted 19 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... === Extracted Relation === Input tokens: [' ', 'Sundar', 'Pichai', ',', 'CEO', ',', 'Alphabet', 'Inc.', ',', 'CEO', ',', 'Alphabet', 'Inc.'] Output Confidence: 0.99198514 ; Subject: Sundar Pichai ; Object: Alphabet Inc. ; Adding to set of extracted relations ========== Processed 5 / 19 sentences Processed 10 / 19 sentences Processed 15 / 19 sentences Extracted annotations for 1 out of total 19 sentences Relations extracted from this website: 1 (Overall: 1) URL ( 9 / 10): https://www.cnbc.com/2024/02/28/google-ceo-tells-employees-gemini-ai-blunder-unacceptable.html Fetching text from url ... Webpage length (num characters): 9240 Annotating the webpage using spacy... Extracted 64 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 64 sentences Processed 10 / 64 sentences Processed 15 / 64 sentences === Extracted Relation === Input tokens: ['TVWatchlistInvesting', 'ClubPROMenuAI', 'ImpactAI', 'ImpactGoogle', 'CEO', 'tells', 'employees', 'Gemini', 'AI', 'blunder', '‘'] Output Confidence: 0.5583124 ; Subject: ImpactGoogle ; Object: Gemini ; Confidence is lower than threshold confidence. Ignoring this. ========== === Extracted Relation === Input tokens: ['Feb', '29', '202410:54', 'AM', 'ESTJennifer', 'Elias@jenn_eliasWATCH', 'LIVEKey', 'PointsGoogle', 'CEO', 'Sundar', 'Pichai', 'said', 'in', 'a', 'memo', 'that', 'the', 'company', 'is', 'working', 'around', 'the', 'clock', 'on', 'a', 'fix', 'for', 'its', 'artificial', 'intelligence', 'image', 'generator', 'tool', '.'] Output Confidence: 0.9957357 ; Subject: Sundar Pichai ; Object: ESTJennifer Elias@jenn_eliasWATCH LIVEKey ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Feb', '29', '202410:54', 'AM', 'ESTJennifer', 'Elias@jenn_eliasWATCH', 'LIVEKey', 'PointsGoogle', 'CEO', 'Sundar', 'Pichai', 'said', 'in', 'a', 'memo', 'that', 'the', 'company', 'is', 'working', 'around', 'the', 'clock', 'on', 'a', 'fix', 'for', 'its', 'artificial', 'intelligence', 'image', 'generator', 'tool', '.'] Output Confidence: 0.9972771 ; Subject: Sundar Pichai ; Object: PointsGoogle ; Adding to set of extracted relations ========== Processed 20 / 64 sentences === Extracted Relation === Input tokens: ['2023.Justin', 'Sullivan', '|', 'Getty', 'Images', 'News', '|', 'Getty', 'ImagesIn', 'a', 'memo', 'Tuesday', 'evening', ',', 'Google', 'CEO', 'Sundar', 'Pichai', 'addressed', 'the', 'company', '’s', 'artificial', 'intelligence', 'mistakes', ','] Output Confidence: 0.9644561 ; Subject: Sundar Pichai ; Object: 2023.Justin Sullivan | Getty Images News ; Adding to set of extracted relations ========== === Extracted Relation === Input tokens: ['Google', 'CEO', 'Sundar', 'Pichai', 'addressed', 'the', 'company', '’s', 'artificial', 'intelligence', 'mistakes', ','] Output Confidence: 0.97939646 ; Subject: Sundar Pichai ; Object: Google ; Duplicate with lower confidence than existing record. Ignoring this. ========== Processed 25 / 64 sentences Processed 30 / 64 sentences Processed 35 / 64 sentences Processed 40 / 64 sentences Processed 45 / 64 sentences Processed 50 / 64 sentences Processed 55 / 64 sentences Processed 60 / 64 sentences Extracted annotations for 2 out of total 64 sentences Relations extracted from this website: 3 (Overall: 5) URL ( 10 / 10): http://abc.xyz/ Fetching text from url ... Webpage length (num characters): 5862 Annotating the webpage using spacy... Extracted 59 sentences. Processing each sentence one by one to check for presence of right pair of named entity types; if so, will run the second pipeline ... Processed 5 / 59 sentences Processed 10 / 59 sentences Processed 15 / 59 sentences Processed 20 / 59 sentences Processed 25 / 59 sentences Processed 30 / 59 sentences Processed 35 / 59 sentences Processed 40 / 59 sentences Processed 45 / 59 sentences Processed 50 / 59 sentences Processed 55 / 59 sentences Extracted annotations for 0 out of total 59 sentences Relations extracted from this website: 0 (Overall: 0) ================== ALL RELATIONS for per:employee_of ( 41 ) ================= Confidence: 0.9973 | Subject: Pichai | Object: Alphabet Confidence: 0.9972771 | Subject: Sundar Pichai | Object: PointsGoogle Confidence: 0.99725914 | Subject: Larry Page | Object: Google Confidence: 0.9970755 | Subject: Pichai | Object: Google Confidence: 0.99695766 | Subject: ofAlphabet Inc.[1]Magic | Object: Alphabet Confidence: 0.9968208 | Subject: Page | Object: Alphabet Confidence: 0.9966107 | Subject: Sundararajan Pichai | Object: Britannica Book of the Year Confidence: 0.99652606 | Subject: Sundar Pichai | Object: executive.[6][7 Confidence: 0.99645483 | Subject: Pichai Sundararajan | Object: Google, Inc. Confidence: 0.9963161 | Subject: Andy Rubin,[32 | Object: Jive Software Confidence: 0.9962886 | Subject: Melinda Shepherd | Object: Britannica Book of the Year Confidence: 0.9960235 | Subject: Pichai | Object: Applied Materials Confidence: 0.9958059 | Subject: Sundar Pichai | Object: Google Confidence: 0.9957357 | Subject: Sundar Pichai | Object: ESTJennifer Elias@jenn_eliasWATCH LIVEKey Confidence: 0.9957271 | Subject: Pichai | Object: the World Internet Conference Confidence: 0.9955069 | Subject: Jack Dorsey | Object: Twitter Confidence: 0.99550307 | Subject: Melinda C. Shepherd | Object: Britannica Book of the Year Confidence: 0.9954632 | Subject: Aravind Srinivas | Object: Perplexity Confidence: 0.99530756 | Subject: Othman Laraki | Object: Color Health Confidence: 0.9950949 | Subject: Pichai | Object: McKinsey & Company.[26 Confidence: 0.995001 | Subject: Sundararajan Pichai | Object: Encyclopædia Britannica Confidence: 0.99497056 | Subject: Aravind Srinivas | Object: OpenAI Confidence: 0.9942706 | Subject: Melinda Shepherd | Object: Encyclopædia Britannica Confidence: 0.9935331 | Subject: Srinivas | Object: Google Confidence: 0.992464 | Subject: Melinda C. Shepherd | Object: Encyclopædia Britannica Confidence: 0.992446 | Subject: Jack Dorsey | Object: Meta Confidence: 0.99198514 | Subject: Sundar Pichai | Object: Alphabet Inc. Confidence: 0.9919569 | Subject: Aravind Srinivas | Object: Google Confidence: 0.98028326 | Subject: Jack Dorsey | Object: Facebook Confidence: 0.97429043 | Subject: Marissa Mayer | Object: Google Confidence: 0.9644561 | Subject: Sundar Pichai | Object: 2023.Justin Sullivan | Getty Images News Confidence: 0.9442318 | Subject: Regunatha Pichai | Object: GEC Confidence: 0.93322414 | Subject: X.Marissa | Object: Google Confidence: 0.9291089 | Subject: Mark Zuckerberg | Object: Twitter Confidence: 0.9186752 | Subject: Mark Zuckerberg | Object: Facebook Confidence: 0.9035453 | Subject: ofAlphabet Inc.[1]Magic | Object: GoogleBoard Confidence: 0.8829768 | Subject: Satya Nadella.[38][39 | Object: Microsoft Confidence: 0.8444577 | Subject: Ruth Porat | Object: SVP Confidence: 0.8257356 | Subject: Sundar Pichai | Object: ScoopGoogle Confidence: 0.78901273 | Subject: Pichai | Object: Twitter Confidence: 0.72635496 | Subject: Mark Zuckerberg | Object: Meta Total # of iterations = 1