Triple

T17747976
Position Surface form Disambiguated ID Type / Status
Subject Epitaph One E443035 entity
Predicate laterAiredOn P11338 FINISHED
Object Syfy UK 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: Syfy UK | Statement: [Epitaph One, laterAiredOn, Syfy UK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Syfy UK
Context triple: [Epitaph One, laterAiredOn, Syfy UK]
  • A. Syfy chosen
    Syfy is an American cable television channel specializing in science fiction, fantasy, horror, and supernatural programming.
  • B. Shudder
    Shudder is a subscription-based streaming service specializing in horror, thriller, and supernatural films and series.
  • C. Epix
    Epix was a premium American cable and streaming television network known for airing recent Hollywood films, original series, and specials before being rebranded as MGM+.
  • D. Orange TV
    Orange TV is a subscription-based television platform operated by the telecommunications company Orange, offering a range of live channels and on-demand content.
  • E. 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.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47ad46a50819089c87f74efe3c7ca completed April 19, 2026, 6:48 a.m.
Created at: April 10, 2026, 10:10 a.m.