Triple

T15907921
Position Surface form Disambiguated ID Type / Status
Subject 61* E385769 entity
Predicate director P255 FINISHED
Object Billy Crystal E11670 NE FINISHED

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: Billy Crystal | Statement: [61*, director, Billy Crystal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Billy Crystal
Context triple: [61*, director, Billy Crystal]
  • A. Billy Crystal chosen
    Billy Crystal is an American comedian, actor, and filmmaker renowned for his stand-up, film roles, and multiple stints hosting the Academy Awards.
  • B. Steve Martin
    Steve Martin is an American comedian, actor, writer, and musician renowned for his influential stand-up comedy, film roles, and contributions to American humor.
  • C. Jerry Stiller
    Jerry Stiller was an American comedian and actor best known for his roles on the sitcoms Seinfeld and The King of Queens and for his long-running comedy partnership with his wife, Anne Meara.
  • D. Harvey Korman
    Harvey Korman was an American comedic actor best known for his work on *The Carol Burnett Show* and in Mel Brooks films such as *Blazing Saddles* and *History of the World, Part I*.
  • E. Henny Youngman
    Henny Youngman was a British-American comedian and violinist famed for his rapid-fire one-liners and the catchphrase "Take my wife—please."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565c11bc819091b1fd85901a832d completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb055307081908a13c98a0e16780c completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:52 a.m.