Triple

T19021576
Position Surface form Disambiguated ID Type / Status
Subject Light My Fire E465498 entity
Predicate hasCoverVersionBy P11142 FINISHED
Object Amii Stewart 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: Amii Stewart | Statement: [Light My Fire, hasCoverVersionBy, Amii Stewart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amii Stewart
Context triple: [Light My Fire, hasCoverVersionBy, Amii Stewart]
  • A. Amii Stewart chosen
    Amii Stewart is an American disco and soul singer best known for her 1979 hit cover of "Knock on Wood."
  • B. Amii
    Amii is a Canadian research institute based in Alberta that focuses on advancing artificial intelligence and machine learning through research, education, and industry collaboration.
  • C. Nathalie Kerr
    Nathalie Kerr is a fictional character from the work "Delicacy," likely serving as a key figure in its narrative.
  • D. Bonnie MacFarlane
    Bonnie MacFarlane is a capable rancher and key supporting character in the Red Dead Redemption series, known for helping John and Jack Marston and representing frontier resilience and independence.
  • E. Chantal Kreviazuk
    Chantal Kreviazuk is a Canadian singer-songwriter and pianist known for her emotive pop-rock ballads and contributions to film and television soundtracks.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6dfa3c88190a057c3385d680cf8 completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.