Triple

T15949976
Position Surface form Disambiguated ID Type / Status
Subject Caprica E386788 entity
Predicate network P2637 FINISHED
Object Syfy E65799 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: Syfy | Statement: [Caprica, network, Syfy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Syfy
Context triple: [Caprica, network, Syfy]
  • 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. NBC Mystery Movie
    NBC Mystery Movie was a popular 1970s American television anthology series that featured rotating mystery and crime drama films, including shows like Columbo, McCloud, and McMillan & Wife.
  • E. Sky Sci-Fi
    Sky Sci-Fi is a British television channel dedicated to science fiction, fantasy, and related genre programming, operated by Sky in the UK and Ireland.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d4c5008190a56ebf8c28f712dc completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffe46d180c81909be66f628d1bdf72 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:53 a.m.