Triple

T20153870
Position Surface form Disambiguated ID Type / Status
Subject Women I’ve Undressed E491503 entity
Predicate subject P450 FINISHED
Object Orry-Kelly NE NERFINISHED

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: Orry-Kelly | Statement: [Women I’ve Undressed, subject, Orry-Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orry-Kelly
Context triple: [Women I’ve Undressed, subject, Orry-Kelly]
  • A. Orry-Kelly chosen
    Orry-Kelly was an acclaimed Australian-born Hollywood costume designer renowned for his work on classic films such as "Some Like It Hot" and "An American in Paris."
  • B. Alvin Patterson
    Alvin Patterson is a Jamaican percussionist best known for his work with Bob Marley and the Wailers and his influential contributions to roots reggae music.
  • C. Art Babbitt
    Art Babbitt was an influential American animator best known for his character animation work at Walt Disney Studios during the Golden Age of animation.
  • D. Bud Westmore
    Bud Westmore was a prominent American Hollywood makeup artist, best known for his extensive work at Universal Studios on classic films and iconic movie monsters.
  • E. Andrew Loomis
    Andrew Loomis was an American illustrator and art instructor best known for his influential mid-20th-century drawing and figure-construction books that have shaped generations of artists.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667de9bec8190836887c86dbcf28d completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.