Triple

T20298119
Position Surface form Disambiguated ID Type / Status
Subject Nuns on the Run E505405 entity
Predicate musicBy P1952 FINISHED
Object Yello 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: Yello | Statement: [Nuns on the Run, musicBy, Yello]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yello
Context triple: [Nuns on the Run, musicBy, Yello]
  • A. Yello chosen
    Yello is a Swiss electronic music duo known for their innovative, sample-heavy sound and hits like "Oh Yeah," which have been widely used in films and commercials.
  • B. Deepcut
    Deepcut is a village in Surrey, England, best known for its military connections and the presence of the Princess Royal Barracks.
  • C. Heaven 17
    Heaven 17 is a British synth-pop band formed in the early 1980s, known for their politically charged lyrics and influential electronic sound on albums like "Penthouse and Pavement."
  • D. Art of Noise
    Art of Noise is a pioneering British avant-garde synth-pop group known for its innovative use of sampling and experimental electronic production in the 1980s.
  • E. Tears for Fears
    Tears for Fears is a British pop-rock band formed in the early 1980s, best known for hits like "Shout," "Everybody Wants to Rule the World," and "Mad World."
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6770a2cec8190912d6b0dbabc78bc completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:16 a.m.