Triple

T20223532
Position Surface form Disambiguated ID Type / Status
Subject Dan Stevens E495318 entity
Predicate memberOf P10 FINISHED
Object Footlights 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: Footlights | Statement: [Dan Stevens, memberOf, Footlights]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Footlights
Context triple: [Dan Stevens, memberOf, Footlights]
  • A. Footlights chosen
    Footlights is the famed Cambridge University theatrical and comedy club known for launching the careers of many prominent British humorists and performers.
  • B. Footlights and Shadows
    Footlights and Shadows is a silent-era film featuring early 20th-century American actress and screen star Olive Thomas.
  • C. Follow the Lights
    Follow the Lights is an EP by Ryan Adams & The Cardinals that blends alt-country and rock with introspective, melodic songwriting.
  • D. The Lights
    The Lights is the popular nickname for Blackpool Illuminations, the famous annual seaside light festival that transforms the English resort town of Blackpool into a major nighttime attraction.
  • E. The Lights Go Down
    "The Lights Go Down" is a song by Electric Light Orchestra featured on their 1981 concept album "Time."
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fd827708190b798a30f4e7d533f completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.