Triple

T19946490
Position Surface form Disambiguated ID Type / Status
Subject Drawing Restraint 9 E479434 entity
Predicate distributor P1951 FINISHED
Object Tartan 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: Tartan Films | Statement: [Drawing Restraint 9, distributor, Tartan Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tartan Films
Context triple: [Drawing Restraint 9, distributor, Tartan Films]
  • A. Tartan Films chosen
    Tartan Films was a UK-based independent film distribution company known for releasing cult, arthouse, and international cinema, particularly Asian extreme films.
  • B. Highland Films
    Highland Films is a film production company best known for producing the acclaimed historical drama "A Man for All Seasons."
  • C. Kestrel Films
    Kestrel Films is a British film production company best known for producing Ken Loach’s acclaimed 1969 drama "Kes."
  • D. Rook Films
    Rook Films is a British independent film production company known for its distinctive, often surreal and genre-bending movies.
  • E. Hartswood Films
    Hartswood Films is a British television production company best known internationally for creating the hit detective series "Sherlock."
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a6725dc81908c55ec5595be6778 completed April 20, 2026, 4:55 p.m.
Created at: April 10, 2026, 1:54 p.m.