Triple

T10837028
Position Surface form Disambiguated ID Type / Status
Subject Hendrix Hart E255785 entity
Predicate hasHalfSibling P54212 FINISHED
Object Kenzo Kash Hart E255786 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: Kenzo Kash Hart | Statement: [Hendrix Hart, hasHalfSibling, Kenzo Kash Hart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kenzo Kash Hart
Context triple: [Hendrix Hart, hasHalfSibling, Kenzo Kash Hart]
  • A. Kenzo Kash Hart chosen
    Kenzo Kash Hart is the young son of American comedian and actor Kevin Hart and his wife Eniko Parrish.
  • B. Kenzo Nakamura
    Kenzo Nakamura is a Japanese judoka and Olympic gold medalist known for his achievements in the lightweight divisions during the 1990s.
  • C. Kenzo Kitakata
    Kenzo Kitakata is a Japanese crime and hardboiled novelist renowned for his gritty, psychologically rich portrayals of yakuza and urban underworld life.
  • D. Kenzo Takada
    Kenzo Takada was a pioneering Japanese fashion designer who founded the Paris-based luxury brand Kenzo, known for its vibrant prints and East-meets-West aesthetic.
  • E. Kenzo Yashima
    Kenzo Yashima is a person notable for bearing the Japanese given name Kenzo.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d746ff70148190b844ab92d796af6c completed April 9, 2026, 6:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7c739708190b0d58fc2d6392c6c completed April 15, 2026, 8:40 p.m.
Created at: April 8, 2026, 9:19 p.m.