Triple

T2217619
Position Surface form Disambiguated ID Type / Status
Subject Focus Features E48067 entity
Predicate predecessor P97 FINISHED
Object USA Films E68170 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: USA Films | Statement: [Focus Features, predecessor, USA Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: USA Films
Context triple: [Focus Features, predecessor, USA Films]
  • A. American cinema
    American cinema is the film industry and body of motion pictures produced in the United States, best known for Hollywood’s global influence on popular culture and filmmaking.
  • B. October Films chosen
    October Films was an American independent film distribution company known for releasing critically acclaimed arthouse and foreign films in the 1990s.
  • C. American independent cinema
    American independent cinema is a movement of U.S. filmmaking characterized by low-budget, artistically driven, and often unconventional films produced outside the major studio system.
  • D. CBS Films
    CBS Films is an American film production and distribution company owned by CBS Corporation, known for releasing a range of mid-budget feature films.
  • E. US
    US is the IATA airline designator code assigned to the former American airline US Airways.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc010bd4c8190ace293b37eac1de5 completed March 7, 2026, 6:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae65594c948190a43bdab03e61c130 completed March 9, 2026, 6:14 a.m.
Created at: March 4, 2026, 7:46 p.m.