Triple

T8438633
Position Surface form Disambiguated ID Type / Status
Subject Quavious Keyate Marshall E199292 entity
Predicate relative P37 FINISHED
Object Kiari Kendrell Cephus E707763 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: Kiari Kendrell Cephus | Statement: [Quavious Keyate Marshall, relative, Kiari Kendrell Cephus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiari Kendrell Cephus
Context triple: [Quavious Keyate Marshall, relative, Kiari Kendrell Cephus]
  • A. Kiari Cephus chosen
    Kiari Cephus, better known by his stage name Offset, is an American rapper and member of the hip hop trio Migos.
  • B. Terria Joseph
    Terria Joseph is an American actress and theater professional best known as the mother of singer-songwriter Alicia Keys.
  • C. Kendal Richardson
    Kendal Richardson is a political figure who ran for mayor in the 2023 Dallas mayoral election.
  • D. Andell Wilkerson
    Andell Wilkerson is a witty, down-to-earth supporting character from the sitcom "Moesha," known for being Moesha's close friend and a source of comic relief and guidance.
  • E. Devereaux Jennings
    Devereaux Jennings was a pioneering cinematographer best known as the founder of the American Society of Cinematographers, a key professional organization in the film industry.
  • 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_69ca8314cd6c8190a6b8c2a1096e18f3 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe135657c81908ed8156fbfbef6ec completed March 31, 2026, 2:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d87403c8190b979af4979e43517 completed April 2, 2026, 7:40 a.m.
Created at: March 30, 2026, 6:08 p.m.