Triple

T9392389
Position Surface form Disambiguated ID Type / Status
Subject Guy Madison E226054 entity
Predicate coStarredWith P14987 FINISHED
Object Andy Devine E251951 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: Andy Devine | Statement: [Guy Madison, coStarredWith, Andy Devine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Devine
Context triple: [Guy Madison, coStarredWith, Andy Devine]
  • A. Andy Devine chosen
    Andy Devine was an American character actor best known for his distinctive raspy voice and roles in numerous Western films and the television series "The Adventures of Wild Bill Hickok."
  • B. Harry Davenport
    Harry Davenport was an American character actor best known for his numerous supporting roles in classic Hollywood films of the 1930s and 1940s.
  • C. Otto Hunte
    Otto Hunte was a prominent German film art director and production designer best known for his influential work on classic Weimar-era films, including Fritz Lang’s Metropolis.
  • D. Wallace Beery
    Wallace Beery was an American actor best known for his gruff yet often lovable screen persona and his Academy Award–winning performance in the film "The Champ" (1931).
  • E. Arthur Coburn
    Arthur Coburn is a film editor best known for his work on major Hollywood productions, including the action-comedy classic "Beverly Hills Cop."
  • 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_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd510eae0c8190b7c4ab487a366bb3 completed April 1, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18208ba9081909efa44f98f90c11a completed April 4, 2026, 9:26 p.m.
Created at: March 30, 2026, 7:45 p.m.