Triple

T17544267
Position Surface form Disambiguated ID Type / Status
Subject Green Porno E427283 entity
Predicate productionCompany P490 FINISHED
Object Sundance Channel 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: Sundance Channel | Statement: [Green Porno, productionCompany, Sundance Channel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sundance Channel
Context triple: [Green Porno, productionCompany, Sundance Channel]
  • A. SundanceTV chosen
    SundanceTV is an American cable and satellite television network known for airing independent films, documentaries, and critically acclaimed original series.
  • B. Sky Channel
    Sky Channel was the original name of Sky One, a British satellite television channel known for airing a mix of entertainment, drama, and imported US programming.
  • C. Paramount Network
    Paramount Network is an American cable television channel owned by Paramount Global, known for airing original scripted series, reality shows, and feature films.
  • D. Fox Channel
    Fox Channel is an international entertainment television network known for airing a mix of popular TV series, movies, and original programming across various global markets.
  • E. Super Channel
    Super Channel is a Canadian premium television network known for broadcasting a mix of original series, films, and international programming.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4545fe29c8190a586c75419fa14ea completed April 19, 2026, 4:04 a.m.
Created at: April 10, 2026, 5:49 a.m.