Triple

T16249413
Position Surface form Disambiguated ID Type / Status
Subject The Manxman E394459 entity
Predicate distributor P1951 FINISHED
Object Wardour Films E394454 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: Wardour Films | Statement: [The Manxman, distributor, Wardour Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wardour Films
Context triple: [The Manxman, distributor, Wardour Films]
  • A. Wardour Films chosen
    Wardour Films was a British film distribution company active in the early 20th century, known for handling the release of numerous silent and early sound films in the United Kingdom.
  • B. Barwood Films
    Barwood Films is a film production company co-founded by Barbra Streisand, known for producing several of her starring and directing projects.
  • C. Waverly Films
    Waverly Films is a Brooklyn-based film and video production collective known for its offbeat comedy shorts, music videos, and collaborations with major studios and brands.
  • D. Euston Films
    Euston Films was a British television production company, best known for its gritty, location-based drama series in the 1970s and 1980s.
  • E. Orchard Films
    Orchard Films is an independent film distribution company known for releasing documentaries and arthouse features.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24594f23c8190bd59fcb2585cb5e3 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ee568a48190835ce76f84461044 completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:04 a.m.