Triple

T15533710
Position Surface form Disambiguated ID Type / Status
Subject All Is Lost E370286 entity
Predicate productionCompany P490 FINISHED
Object Washington Square Films E512547 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: Washington Square Films | Statement: [All Is Lost, productionCompany, Washington Square Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Washington Square Films
Context triple: [All Is Lost, productionCompany, Washington Square Films]
  • A. Washington Square Films chosen
    Washington Square Films is an American independent film production company known for backing critically acclaimed, character-driven movies.
  • B. Greenpoint Films
    Greenpoint Films is a film production company best known for producing the acclaimed period drama "Enchanted April."
  • C. Pearl Street Films
    Pearl Street Films is a film and television production company co-founded by actors Ben Affleck and Matt Damon, known for producing a range of high-profile projects.
  • D. Roxbury Pictures
    Roxbury Pictures is a film production company known for producing the movie "Enemy."
  • E. Grass Root Film Company
    Grass Root Film Company is an Indian film production house known for backing acclaimed Tamil-language films, established by director Vetrimaaran.
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0414877d88190804ee76566004e13 completed April 16, 2026, 1:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d5e82a48190bb0a10ebc2412129 completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 4:06 a.m.