Triple

T6966912
Position Surface form Disambiguated ID Type / Status
Subject Adrienne Barbeau E161511 entity
Predicate notableWork P4 FINISHED
Object Creepshow E136823 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: Creepshow | Statement: [Adrienne Barbeau, notableWork, Creepshow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Creepshow
Context triple: [Adrienne Barbeau, notableWork, Creepshow]
  • A. Creepshow chosen
    Creepshow is a 1982 horror-comedy anthology film directed by George A. Romero and written by Stephen King, paying homage to 1950s EC horror comics through a series of macabre, darkly humorous stories.
  • B. Creepshow 2
    Creepshow 2 is a 1987 horror anthology film featuring multiple Stephen King–based stories presented in a comic book style, serving as the follow-up to the original Creepshow.
  • C. Creepshow 3
    Creepshow 3 is a 2006 direct-to-video horror anthology film loosely connected to the original Creepshow movies, featuring several interwoven darkly comic tales.
  • D. Dead of Night
    Dead of Night is a 1945 British anthology horror film renowned for its influential blend of psychological terror and supernatural tales, including the famous ventriloquist dummy segment.
  • E. Creepshow (TV series)
    Creepshow is a horror anthology television series inspired by the 1982 film of the same name, featuring standalone episodes that blend campy, comic-book-style storytelling with gruesome and supernatural tales.
  • 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_69c68853cff881908439d488924a8283 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db121174819098e73e45f6c9cc91 completed March 27, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761908564819084505f0ab1122a9c completed March 28, 2026, 5:05 a.m.
Created at: March 27, 2026, 2:30 p.m.