Triple

T10225463
Position Surface form Disambiguated ID Type / Status
Subject Stealing Beauty E243192 entity
Predicate mainCharacter P1183 FINISHED
Object Lucy Harmon E243198 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: Lucy Harmon | Statement: [Stealing Beauty, mainCharacter, Lucy Harmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucy Harmon
Context triple: [Stealing Beauty, mainCharacter, Lucy Harmon]
  • A. Lucy Harmon chosen
    Lucy Harmon is the introspective American teenager at the center of Bernardo Bertolucci's 1996 film "Stealing Beauty," portrayed by Liv Tyler in one of her most acclaimed early roles.
  • B. Lucy Wyman
    Lucy Wyman is a key character in the romantic comedy film "13 Going on 30," serving as the adult version of Jenna Rink’s former best friend turned rival in the fashion magazine world.
  • C. Lucy McCallum
    Lucy McCallum is an Australian jurist who serves as the Chief Justice of the Supreme Court of the Australian Capital Territory.
  • D. Lucy Lamar
    Lucy Lamar was the wife of prominent Mississippi politician and U.S. Senator Pat Harrison.
  • E. Lucy Osburn
    Lucy Osburn was a pioneering English nurse and hospital reformer who helped establish modern nursing practices in Australia in the 19th century.
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d1f9cf6c81909a6b9e9b9d0a79fe completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d74fd5df188190b5ad2e57abeb6b13 completed April 9, 2026, 7:05 a.m.
Created at: April 6, 2026, 11:17 a.m.