Triple

T2008262
Position Surface form Disambiguated ID Type / Status
Subject Yolanda and the Thief E43633 entity
Predicate setDecorationBy P22426 FINISHED
Object Edwin B. Willis E592761 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: Edwin B. Willis | Statement: [Yolanda and the Thief, setDecorationBy, Edwin B. Willis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edwin B. Willis
Context triple: [Yolanda and the Thief, setDecorationBy, Edwin B. Willis]
  • A. Edwin B. Willis chosen
    Edwin B. Willis was an American art director and set decorator renowned for his work on numerous classic Hollywood films, particularly at MGM.
  • B. Edwin T. Meredith
    Edwin T. Meredith was an American publisher and politician who served as U.S. Secretary of Agriculture under President Woodrow Wilson.
  • C. Harry M. Wegeforth
    Harry M. Wegeforth was an American physician and civic leader best known for establishing and guiding the early development of the San Diego Zoo into a major zoological institution.
  • D. Charles F. Wheeler
    Charles F. Wheeler was an American cinematographer known for his work on feature films and television during the mid-20th century.
  • E. Eugene C. Bingham
    Eugene C. Bingham was an American chemist and pioneer in rheology whose work on the flow and deformation of materials led to the establishment of a prestigious scientific award in his honor.
  • 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_69a88716e9f08190946313fdc949e3cf completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbdbe35688190ab99620859e071c6 completed March 7, 2026, 5:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69c6536fc20c81909b6c57d559880877 completed March 27, 2026, 9:52 a.m.
Created at: March 4, 2026, 7:37 p.m.