Triple

T21481183
Position Surface form Disambiguated ID Type / Status
Subject Tom Selleck E529996 entity
Predicate birthName P65 FINISHED
Object Thomas William Selleck NE NERFINISHED

How this triple was built (2 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 William Selleck | Statement: [Tom Selleck, birthName, Thomas William Selleck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas William Selleck
Context triple: [Tom Selleck, birthName, Thomas William Selleck]
  • A. Tom Selleck chosen
    Tom Selleck is an American actor best known for his starring role as private investigator Thomas Magnum in the television series "Magnum, P.I."
  • B. Robert Davi
    Robert Davi is an American actor, singer, and director best known for his tough-guy roles in films such as "Die Hard" and the James Bond movie "Licence to Kill."
  • C. Richard Gere
    Richard Gere is an American actor known for his leading roles in films such as "American Gigolo," "An Officer and a Gentleman," and "Pretty Woman."
  • D. Ian George
    Ian George is an Australian Anglican bishop who served as the Archbishop of Adelaide, leading the Anglican Church in South Australia.
  • E. Jeremy Grey
    Jeremy Grey is a charismatic, fast-talking divorce mediator and womanizer portrayed by Vince Vaughn in the comedy film "Wedding Crashers."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45acc3881908e38d3f28964152b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea338f988190a3044f8d02a567fe completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:21 p.m.