Triple

T15122179
Position Surface form Disambiguated ID Type / Status
Subject Changes E361195 entity
Predicate featuresArtist P1952 FINISHED
Object Kehlani E190513 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: Kehlani | Statement: [Changes, featuresArtist, Kehlani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kehlani
Context triple: [Changes, featuresArtist, Kehlani]
  • A. Kehlani chosen
    Kehlani is an American R&B singer, songwriter, and performer known for her emotive vocals, candid lyricism, and genre-blending projects like the mixtape "You Should Be Here" and the album "SweetSexySavage."
  • B. Kimbra
    Kimbra is a New Zealand singer, songwriter, and producer known for her eclectic pop style and for her Grammy-winning collaboration on Gotye’s hit single "Somebody That I Used to Know."
  • C. Jhené Aiko
    Jhené Aiko is an American singer and songwriter known for her ethereal vocals and introspective, R&B-influenced music.
  • D. Alina Baraz
    Alina Baraz is an American singer and songwriter known for her atmospheric, R&B-influenced electronic pop and collaborations with producers like Galimatias.
  • E. Hayley Kiyoko
    Hayley Kiyoko is an American singer, songwriter, and actress known for her pop music career and prominent LGBTQ+ representation in her work.
  • 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_69d85a06450081909c5a14ea9851a15e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0059f69a881909929a037a0eef702 completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff01d9af308190b0103cec0fb8d87d completed May 9, 2026, 9:43 a.m.
Created at: April 10, 2026, 3:06 a.m.