Triple

T22541291
Position Surface form Disambiguated ID Type / Status
Subject Across the Universe E557293 entity
Predicate productionCompany P490 FINISHED
Object Fortis Films 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: Fortis Films | Statement: [Across the Universe, productionCompany, Fortis Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fortis Films
Context triple: [Across the Universe, productionCompany, Fortis Films]
  • A. Fortis Films chosen
    Fortis Films is a film and television production company founded by actress Sandra Bullock, known for producing projects such as the Miss Congeniality films.
  • B. Vistar Films
    Vistar Films is a film production company best known for its involvement in the making of the 1985 horror-comedy classic "Fright Night."
  • C. Aquarius Films
    Aquarius Films is an Australian film and television production company known for creating distinctive, character-driven screen content for both local and international audiences.
  • D. Cascade Films
    Cascade Films is a film production company known for developing and producing independent feature films.
  • E. Pantelion Films
    Pantelion Films is a film production and distribution company known for specializing in Latino-focused and Spanish-language movies, formed as a joint venture between Lionsgate and Televisa.
  • 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_69e11e58662081909ae346ab384514ca completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f3251808190a72b849157854d8d completed April 29, 2026, 1:30 a.m.
Created at: April 16, 2026, 8:51 p.m.