Triple

T16770793
Position Surface form Disambiguated ID Type / Status
Subject Trevor Engelson E407588 entity
Predicate employer P7 FINISHED
Object Underground Films E1086915 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: Underground Films | Statement: [Trevor Engelson, employer, Underground Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Underground Films
Context triple: [Trevor Engelson, employer, Underground Films]
  • A. Underground Films chosen
    Underground Films is a film production company known for producing feature films such as the romantic drama "Remember Me."
  • B. Pariah Films
    Pariah Films is a film production company best known for producing the Australian crime drama film "Chopper."
  • C. Shoebox Films
    Shoebox Films is a British film production company known for producing independent and auteur-driven movies, including the 2019 thriller "Serenity."
  • D. Pandemonium Films
    Pandemonium Films is a film production company known for producing the 2005 supernatural horror movie "Dark Water."
  • E. The Cinematic Underground
    The Cinematic Underground is an experimental music and multimedia collective known for its atmospheric, narrative-driven soundscapes and close association with composer Nathan Johnson’s film and art projects.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b0361e5081908f58edf766ff3ce0 completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a5361c3881909be0fb9b83a59993 completed May 10, 2026, 3:33 p.m.
Created at: April 10, 2026, 5:21 a.m.