Triple

T6868481
Position Surface form Disambiguated ID Type / Status
Subject Susan Downey E158476 entity
Predicate employer P7 FINISHED
Object Dark Castle Entertainment E197245 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: Dark Castle Entertainment | Statement: [Susan Downey, employer, Dark Castle Entertainment]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dark Castle Entertainment
Context triple: [Susan Downey, employer, Dark Castle Entertainment]
  • A. Dark Castle Entertainment chosen
    Dark Castle Entertainment is an American film production company known for producing genre films, particularly horror and action thrillers.
  • B. Longcross Studios
    Longcross Studios is a major British film and television production facility in Surrey, England, known for hosting large-scale Hollywood and high-end TV shoots.
  • C. Necropia Entertainment
    Necropia Entertainment is a film production company known for working on projects such as the 2020 adaptation of "The Witches."
  • D. Troublemaker Studios
    Troublemaker Studios is an American film production company founded by director Robert Rodriguez, known for producing action-packed and genre-blending movies such as the "Spy Kids" and "Machete" series.
  • E. Outpost Entertainment
    Outpost Entertainment is a television and film production company known for creating unscripted and documentary-style content.
  • 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_69c68831e3648190a643c328122e4d43 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d8a793a481909340239c065393a4 completed March 27, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c74299ae148190a56c7b1ee8829f40 completed March 28, 2026, 2:53 a.m.
Created at: March 27, 2026, 2:22 p.m.