Triple

T10071933
Position Surface form Disambiguated ID Type / Status
Subject Frances Stevens E213649 entity
Predicate romanticInterest P7325 FINISHED
Object John Robie E400707 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: John Robie | Statement: [Frances Stevens, romanticInterest, John Robie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Robie
Context triple: [Frances Stevens, romanticInterest, John Robie]
  • A. John Robie chosen
    John Robie is a retired jewel thief known as "The Cat" who becomes embroiled in a new string of robberies on the French Riviera in Alfred Hitchcock's film "To Catch a Thief."
  • B. Norman Reilly Raine
    Norman Reilly Raine was an American screenwriter and playwright best known for his Academy Award-winning work on classic Hollywood films such as the 1938 adventure epic "The Adventures of Robin Hood."
  • C. Peter James
    Peter James is an Australian cinematographer known for his work on numerous feature films and television projects.
  • D. Peter James
    Peter James is a bestselling British crime and thriller novelist, best known for his Roy Grace detective series.
  • E. Raymond Gardner
    Raymond Gardner was the brother of famed American actress Ava Gardner, a member of the Gardner family from rural North Carolina.
  • 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd01279388190b94c8def00425c78 completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29aaa61308190b134b49a6c1c1131 completed April 5, 2026, 5:23 p.m.
Created at: March 30, 2026, 8:59 p.m.