Triple

T2436633
Position Surface form Disambiguated ID Type / Status
Subject Mervyn LeRoy E52975 entity
Predicate employer P7 FINISHED
Object Warner Bros. E124965 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: Warner Bros. | Statement: [Mervyn LeRoy, employer, Warner Bros.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Warner Bros.
Context triple: [Mervyn LeRoy, employer, Warner Bros.]
  • A. Warner Bros. Entertainment chosen
    Warner Bros. Entertainment is a major American film and television studio and media company known for producing blockbuster franchises and owning prominent entertainment brands such as DC Comics.
  • B. Warner Bros. Pictures
    Warner Bros. Pictures is a major American film production and distribution studio known for releasing numerous blockbuster movies across a wide range of genres.
  • C. Warner Sogefilms
    Warner Sogefilms is a Spanish film distribution company associated with releasing major domestic and international titles.
  • D. Warner
    Warner is a common English surname borne by numerous notable individuals across literature, entertainment, sports, and public life.
  • E. Warner Bros. Animation
    Warner Bros. Animation is a major American animation studio best known for producing Looney Tunes, DC Comics animated projects, and other television and direct-to-video cartoons.
  • 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_69ab4959bcc0819083246f9fb10439e3 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc9cd49b48190bff10a5ab7cef483 completed March 7, 2026, 6:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69b055827da881909a589a8d5c577eb9 completed March 10, 2026, 5:31 p.m.
Created at: March 6, 2026, 9:43 p.m.