Triple

T10954820
Position Surface form Disambiguated ID Type / Status
Subject Damn Yankees E258816 entity
Predicate costumeDesigner P184 FINISHED
Object Howard Shoup E594230 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: Howard Shoup | Statement: [Damn Yankees, costumeDesigner, Howard Shoup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Shoup
Context triple: [Damn Yankees, costumeDesigner, Howard Shoup]
  • A. Howard Shoup chosen
    Howard Shoup was an American costume designer known for his prolific work in Hollywood films from the 1940s through the 1960s and for receiving multiple Academy Award nominations.
  • B. Mike Davis
    Mike Davis is an American college basketball coach best known for succeeding Bob Knight at Indiana University and leading the Hoosiers to the 2002 NCAA championship game.
  • C. Mike Davis
    Mike Davis was an American Marxist urban theorist, historian, and writer best known for his incisive analyses of cities, capitalism, and environmental catastrophe.
  • D. Larry Dolan
    Larry Dolan is an American lawyer and businessman best known as the principal owner of Major League Baseball’s Cleveland Guardians (formerly Indians).
  • E. Howard Klein
    Howard Klein is a television producer known for his work on acclaimed series such as Carnivàle.
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770ff718c81909d4baebea3b56b83 completed April 9, 2026, 9:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23c72196c8190b2336a130b64ab8e completed April 17, 2026, 1:58 p.m.
Created at: April 8, 2026, 9:23 p.m.