Triple

T18093442
Position Surface form Disambiguated ID Type / Status
Subject Down by Law E433026 entity
Predicate distributor P1951 FINISHED
Object Island Pictures 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: Island Pictures | Statement: [Down by Law, distributor, Island Pictures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Island Pictures
Context triple: [Down by Law, distributor, Island Pictures]
  • A. Island Pictures chosen
    Island Pictures was an independent film distribution company known for releasing notable arthouse and independent films in the 1980s.
  • B. Harbour Pictures
    Harbour Pictures is a British film production company best known for producing the hit comedy-drama "Calendar Girls."
  • C. Empire Pictures
    Empire Pictures was an independent American film production and distribution company best known for low-budget horror, fantasy, and science fiction movies in the 1980s.
  • D. Prospero Pictures
    Prospero Pictures is a Canadian film production company known for backing independent and auteur-driven films, including works by director David Cronenberg.
  • E. Caravan Pictures
    Caravan Pictures was an American film production company active in the 1990s, known for producing a range of mainstream Hollywood movies under the leadership of executive Joe Roth.
  • 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_69d8b907d05c819083cc3bd6021089e6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dd1a75048190924ebc01da83851b completed April 19, 2026, 1:48 p.m.
Created at: April 10, 2026, 10:27 a.m.