Triple

T9750443
Position Surface form Disambiguated ID Type / Status
Subject Tom Osborne E236426 entity
Predicate givenName P17 FINISHED
Object Thomas
Thomas is the full given name of Tom Osborne, the renowned former University of Nebraska football coach and U.S. congressman.
E819454 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 Osborne, givenName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas
Context triple: [Tom Osborne, givenName, Thomas]
  • A. John
    John is the husband of Martha Rainsborough.
  • B. John
    John is the given name of Colonel John Quincy, an American military officer and politician after whom John Quincy Adams was named.
  • C. John
    John is the first name of J. Michael Luttig, a prominent American conservative jurist and former federal appellate judge.
  • D. John
    John is the given name of John Vlissides, a software engineer best known as one of the “Gang of Four” authors of the influential book *Design Patterns: Elements of Reusable Object-Oriented Software*.
  • E. John
    John I, Count Palatine of Simmern, was a 15th-century German nobleman of the House of Wittelsbach who ruled the Palatinate-Simmern region within the Holy Roman Empire.
  • 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 Osborne, givenName, Thomas]
Generated description
Thomas is the full given name of Tom Osborne, the renowned former University of Nebraska football coach and U.S. congressman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas
Target entity description: Thomas is the full given name of Tom Osborne, the renowned former University of Nebraska football coach and U.S. congressman.
  • A. Thomas
    Thomas is the full given name of Tom Brady, the legendary NFL quarterback widely regarded as one of the greatest players in American football history.
  • B. Thomas
    Thomas is the given first name of American football coach and politician Tommy Tuberville.
  • C. Thomas
    Thomas is the given first name of Tom Flores, the former American football quarterback and Super Bowl–winning head coach.
  • D. Thomas
    Thomas is the formal given name of Tom Vilsack, an American politician who has served multiple terms as U.S. Secretary of Agriculture.
  • E. Thomas
    Thomas is the formal given name of Tom Coughlin, the American football coach best known for leading the New York Giants to two Super Bowl victories.
  • 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_69ca84d4eddc8190996fec1417d2bae8 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f6bb4088190ab8d52ef61d24bee completed April 1, 2026, 10:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bcc45bfc81909b86d10598d9bd39 completed April 5, 2026, 1:37 a.m.
NEDg Description generation batch_69d1bd42e3888190b13970710a9620d7 completed April 5, 2026, 1:39 a.m.
NED2 Entity disambiguation (via description) batch_69d1bdd5ec94819083edd1cb2c9598a0 completed April 5, 2026, 1:41 a.m.
Created at: March 30, 2026, 8:24 p.m.