Triple

T21119366
Position Surface form Disambiguated ID Type / Status
Subject Brian Kavanaugh-Jones E520384 entity
Predicate notableWork P4 FINISHED
Object The Black Phone 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: The Black Phone | Statement: [Brian Kavanaugh-Jones, notableWork, The Black Phone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Black Phone
Context triple: [Brian Kavanaugh-Jones, notableWork, The Black Phone]
  • A. The Black Phone chosen
    The Black Phone is a horror short story by Joe Hill about a kidnapped boy who receives ghostly phone calls from the killer’s previous victims.
  • B. The Night House
    The Night House is a 2020 psychological horror film in which Rebecca Hall plays a grieving widow uncovering disturbing secrets about her late husband and their lakeside home.
  • C. Don’t Breathe
    Don’t Breathe is a 2016 American horror-thriller film about a group of burglars who become trapped in the home of a blind but deadly man.
  • D. The Babadook
    The Babadook is a 2014 Australian psychological horror film about a grieving mother and her troubled son who are terrorized by a sinister entity emerging from a mysterious children's pop-up book.
  • E. Boogeyman
    Boogeyman is a 2005 supernatural horror film about a man confronting the childhood monster he believes killed his father.
  • 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_69e0b50a623881909c0bbaf4f2c055e7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7223176c48190bfbaea41c2209a15 completed April 21, 2026, 7:07 a.m.
Created at: April 16, 2026, 2:55 p.m.