Triple

T16496964
Position Surface form Disambiguated ID Type / Status
Subject John Robie E400707 entity
Predicate romanticInterest P7325 FINISHED
Object Frances Stevens E213649 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: Frances Stevens | Statement: [John Robie, romanticInterest, Frances Stevens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frances Stevens
Context triple: [John Robie, romanticInterest, Frances Stevens]
  • A. Frances Stevens chosen
    Frances Stevens is a fictional socialite character best known as Grace Kelly’s witty and glamorous role in Alfred Hitchcock’s 1955 film "To Catch a Thief."
  • B. Ann Stevens
    Ann Stevens is the mother of American actor George Hamilton.
  • C. Elizabeth Stevens
    Elizabeth Stevens is known as the daughter of the late U.S. Supreme Court Justice John Paul Stevens.
  • D. Jan Stevens
    Jan Stevens is a composer best known for creating music for the television series "Scrubs."
  • E. Frances Johnston
    Frances Johnston was the wife of James Iredell Jr., a governor of North Carolina and associate justice of the United States Supreme Court.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e343a7c81909e04cbaaa40e2531 completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0084ac013c81909ce7055de4f12e58 completed May 10, 2026, 1:14 p.m.
Created at: April 10, 2026, 5:14 a.m.