Triple

T19859433
Position Surface form Disambiguated ID Type / Status
Subject Ghosteen E477216 entity
Predicate track P17929 FINISHED
Object Ghosteen Speaks 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: Ghosteen Speaks | Statement: [Ghosteen, track, Ghosteen Speaks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghosteen Speaks
Context triple: [Ghosteen, track, Ghosteen Speaks]
  • A. Ghosteen chosen
    Ghosteen is a double album by Nick Cave and the Bad Seeds, noted for its ethereal sound and deeply meditative exploration of grief and transcendence.
  • B. Ghosteen – Part 1
    Ghosteen – Part 1 is the first half of Nick Cave and the Bad Seeds’ 2019 double album Ghosteen, featuring ethereal, narrative-driven songs that explore grief, loss, and transcendence.
  • C. Ghosteen Ltd
    Ghosteen Ltd is a company associated with the music and artistic projects surrounding Nick Cave & The Bad Seeds’ album "Ghosteen."
  • D. Headful of Ghosts
    Headful of Ghosts is a song by the American rock band Golden State.
  • E. Beautiful Ghosts
    "Beautiful Ghosts" is an original song co-written by Taylor Swift and Andrew Lloyd Webber for the 2019 film adaptation of the musical Cats.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6586e8b648190bb650d7f2816dda1 completed April 20, 2026, 4:46 p.m.
Created at: April 10, 2026, 1:51 p.m.