Triple

T29926181
Position Surface form Disambiguated ID Type / Status
Subject Fire on Babylon E760084 entity
Predicate fromCountryArtist P71623 FINISHED
Object Irish singer-songwriter LITERAL 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: Irish singer-songwriter | Statement: [Fire on Babylon, fromCountryArtist, Irish singer-songwriter]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fromCountryArtist
Context triple: [Fire on Babylon, fromCountryArtist, Irish singer-songwriter]
  • A. hasCountryArtist
    Indicates a relationship where an entity is associated with, represented by, or features a specific country music artist.
  • B. associated artist nationality chosen
    Indicates the country or nationality with which an artist connected to the subject is identified.
  • C. featuredArtistNationality
    Indicates the nationality associated with an artist who is prominently featured in a work or event.
  • D. coArtistNationality
    Indicates that two artists who have collaborated share the same nationality.
  • E. composerCountry
    Indicates the country with which a composer is associated, typically by birth, citizenship, or primary activity.
  • F. None of above.

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_69f224631674819080c8d089674f9f4f completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f67797fe5c81909575b762f32b63ef completed May 2, 2026, 10:15 p.m.
PD Predicate disambiguation batch_69f66ec8298c8190b41fe9d182c05676 completed May 2, 2026, 9:38 p.m.
Created at: April 29, 2026, 6:16 p.m.