Triple

T18276850
Position Surface form Disambiguated ID Type / Status
Subject Tom Coburn E437758 entity
Predicate givenName P17 FINISHED
Object Thomas
Thomas is the given first name of Tom Coburn, the American physician and Republican politician who served in both the U.S. House of Representatives and the U.S. Senate.
E1315206 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Thomas | Statement: [Tom Coburn, givenName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas
Context triple: [Tom Coburn, givenName, Thomas]
  • A. Thomas
    Thomas is the given name of Sir Stamford Raffles, the British statesman best known as the founder of modern Singapore.
  • B. Thomas
    Thomas is the given name of British entertainer Tommy Steele, a pioneering rock and roll singer and actor.
  • C. Thomas
    Thomas is a character in Simon Gray's stage play "Quartermaine's Terms," which explores the personal and professional lives of teachers at a 1960s Cambridge language school.
  • D. Thomas
    Thomas is a character appearing in the animated series "Exit 9B" from the show "Regular Show."
  • E. Thomas
    Thomas is the first name of American novelist Tom Clancy, famed for his military and espionage thrillers such as "The Hunt for Red October" and "Patriot Games."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Thomas
Triple: [Tom Coburn, givenName, Thomas]
Generated description
Thomas is the given first name of Tom Coburn, the American physician and Republican politician who served in both the U.S. House of Representatives and the U.S. Senate.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas
Target entity description: Thomas is the given first name of Tom Coburn, the American physician and Republican politician who served in both the U.S. House of Representatives and the U.S. Senate.
  • A. Thomas
    Thomas is the given name of American politician Tom Tancredo, a former U.S. Representative from Colorado known for his hardline stance on immigration.
  • B. Thomas
    Thomas is the given first name of Tip O'Neill, the long-serving Speaker of the United States House of Representatives.
  • C. Thomas
    Thomas is the first name of Slade Gorton, an American politician who served as a U.S. Senator from Washington.
  • D. Thomas
    Thomas is the first name of Jeb Hensarling, an American politician who represented Texas in the U.S. House of Representatives and chaired the House Financial Services Committee.
  • E. Thomas
    Thomas is the given name of American politician Tom DeLay, a former House Majority Leader known for his influential role in U.S. Republican politics in the 1990s and early 2000s.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e500528bb88190a9f9ba6428cc2076 completed April 19, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03b3e8bc28819086254e3a03aed2e6 completed May 12, 2026, 11:12 p.m.
NEDg Description generation batch_6a03b4bb6ae48190a68c2a3314f0d3ba completed May 12, 2026, 11:16 p.m.
NED2 Entity disambiguation (via description) batch_6a03b56958a0819088613a9726c71819 completed May 12, 2026, 11:19 p.m.
Created at: April 10, 2026, 10:34 a.m.