Triple

T13747365
Position Surface form Disambiguated ID Type / Status
Subject Kanye West Sunday Service E330248 entity
Predicate performedSong P11145 FINISHED
Object Selah E65949 NE 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: Selah | Statement: [Kanye West Sunday Service, performedSong, Selah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Selah
Context triple: [Kanye West Sunday Service, performedSong, Selah]
  • A. Selah chosen
    "Selah" is a gospel-influenced hip-hop track by Kanye West from his 2019 album *Jesus Is King*, known for its intense choral arrangements and religious themes.
  • B. Selah
    Selah is a contemporary Christian music trio known for their powerful vocal harmonies and modern arrangements of traditional hymns.
  • C. Hymnen
    Hymnen is a large-scale electronic composition by Karlheinz Stockhausen that weaves together and transforms national anthems into an experimental, multi-channel sound collage.
  • D. Hymnes
    Hymnes is a modernist orchestral composition by Igor Markevitch, noted for its complex rhythms and innovative harmonic language.
  • E. Hymnes
    Hymnes is a collection of Renaissance poems by Pierre de Ronsard that blends classical mythology with humanist themes in richly ornate French verse.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02132a108190aca728b95e83af01 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a854098c8190983d142c9930962b completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:08 p.m.