Triple

T23191107
Position Surface form Disambiguated ID Type / Status
Subject Keke Wyatt E579735 entity
Predicate name P16 FINISHED
Object Keke Wyatt 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: Keke Wyatt | Statement: [Keke Wyatt, name, Keke Wyatt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keke Wyatt
Context triple: [Keke Wyatt, name, Keke Wyatt]
  • A. Keke Wyatt chosen
    Keke Wyatt is an American R&B singer and television personality known for her powerful vocals, emotional ballads, and appearances on reality shows like "R&B Divas."
  • B. Jessica Mauboy
    Jessica Mauboy is an Australian singer, songwriter, and actress who rose to fame on Australian Idol and has since become a prominent pop and R&B artist and television personality.
  • C. Kylie Platt
    Kylie Platt is a fictional character from the British soap opera "Coronation Street," known for her turbulent personal life and complex family relationships.
  • D. Climie Fisher
    Climie Fisher was a British pop duo from the late 1980s, best known for their hit singles "Love Changes (Everything)" and "Rise to the Occasion."
  • E. Kylie Peppler
    Kylie Peppler is a learning sciences researcher known for her work on creative computing, maker education, and the integration of arts and technology in STEM learning.
  • 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_69e24600eed08190bd7e5295653a1503 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18fd777c08190bf79e38844fedf27 completed April 29, 2026, 4:57 a.m.
Created at: April 17, 2026, 4:05 p.m.