Triple

T3017745
Position Surface form Disambiguated ID Type / Status
Subject Lost Horizon E82377 entity
Predicate producer P490 FINISHED
Object Harry Cohn E104461 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: Harry Cohn | Statement: [Lost Horizon, producer, Harry Cohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Cohn
Context triple: [Lost Horizon, producer, Harry Cohn]
  • A. Harry Cohn chosen
    Harry Cohn was an American film studio executive and producer who co-founded and long led Columbia Pictures, shaping it into a major Hollywood studio.
  • B. Harry Warner
    Harry Warner was an American film executive and one of the founding brothers of the Warner Bros. studio, a major force in early Hollywood cinema.
  • C. Louis B. Mayer
    Louis B. Mayer was a powerful Hollywood film producer and studio executive who co-founded Metro-Goldwyn-Mayer (MGM) and became one of the most influential figures of the studio era.
  • D. Jack Warner
    Jack Warner was a prominent American film executive and co-founder of Warner Bros. who played a key role in shaping Hollywood’s studio era.
  • E. Sam Spiegel
    Sam Spiegel was an acclaimed Austrian-American film producer known for epic classics such as "Lawrence of Arabia," "The Bridge on the River Kwai," and "On the Waterfront."
  • 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_69ad8b1eb53481908c39bbcd1ec104b2 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a90ea64819080620e60bbd6aa24 completed March 8, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f8663fb881909d7c179f4f61d313 completed March 11, 2026, 11:19 p.m.
Created at: March 8, 2026, 3 p.m.