Triple

T23068111
Position Surface form Disambiguated ID Type / Status
Subject Goon E575108 entity
Predicate distributor P1951 FINISHED
Object Alliance 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: Alliance Films | Statement: [Goon, distributor, Alliance Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alliance Films
Context triple: [Goon, distributor, Alliance Films]
  • A. Alliance Films chosen
    Alliance Films was a major Canadian film distribution and production company known for releasing a wide range of independent and international movies in Canada and other markets.
  • 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. Overture Films
    Overture Films was an American independent film production and distribution company active in the late 2000s, known for releasing a range of mid-budget and specialty films.
  • D. Icon Films
    Icon Films is a British television production company known for creating popular factual and wildlife documentary series, including the hit show "River Monsters."
  • E. Alliance Releasing
    Alliance Releasing was a film distribution company known for handling the release of various independent and international films.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a5aa4081909b3f0dc92877323d completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.