Triple

T22454371
Position Surface form Disambiguated ID Type / Status
Subject Marques Houston as Kevin Barnes E555074 entity
Predicate productionCompany P490 FINISHED
Object Mecca 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: Mecca Films | Statement: [Marques Houston as Kevin Barnes, productionCompany, Mecca Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mecca Films
Context triple: [Marques Houston as Kevin Barnes, productionCompany, Mecca Films]
  • A. Mecca Films chosen
    Mecca Films is a film production company best known for producing the 2004 hip-hop dance drama movie "You Got Served."
  • B. Levantine Films
    Levantine Films is an independent film production company known for backing acclaimed, socially conscious movies such as "Hidden Figures."
  • C. Maddin Films
    Maddin Films is a film production company associated with the work of Canadian avant-garde filmmaker Guy Maddin.
  • D. Swaka Films
    Swaka Films is a film production company known for producing the 2013 adaptation of "Romeo & Juliet."
  • E. Farah Films
    Farah Films is a film and television production company known for working on genre projects such as the fantasy series "The Shannara Chronicles."
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4e2bd4819083e5bed44e9776c6 completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.