Triple

T3653296
Position Surface form Disambiguated ID Type / Status
Subject On the Basis of Sex E77470 entity
Predicate distributor P1951 FINISHED
Object Focus Features E48067 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: Focus Features | Statement: [On the Basis of Sex, distributor, Focus Features]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Focus Features
Context triple: [On the Basis of Sex, distributor, Focus Features]
  • A. Focus Features chosen
    Focus Features is an American film production and distribution company known for releasing critically acclaimed independent and art-house movies.
  • B. Marché du Film
    Marché du Film is the Cannes Film Festival’s major international film market, where industry professionals buy, sell, and promote films and projects.
  • C. Direct Cinema
    Direct Cinema is a documentary filmmaking movement characterized by unobtrusive, observational techniques that aim to capture reality as it unfolds without scripted narration or interference.
  • D. New Yorker Films
    New Yorker Films is an American film distribution company known for bringing international, independent, and art-house cinema to U.S. audiences.
  • E. Cinéfondation
    Cinéfondation is a Cannes Film Festival program dedicated to discovering and promoting emerging filmmakers, primarily through showcasing short and medium-length films from film schools around the world.
  • 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_69ad85def5cc8190863dccf55a18bebb completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc3b805a48190a7bc230a382365d6 completed March 8, 2026, 6:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f4541dc8190b794eae019dcffbf completed March 13, 2026, 5:54 p.m.
Created at: March 8, 2026, 3:24 p.m.