Triple

T22093415
Position Surface form Disambiguated ID Type / Status
Subject Ata Johnson E545963 entity
Predicate relative P37 FINISHED
Object Sika Anoa'i 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: Sika Anoa'i | Statement: [Ata Johnson, relative, Sika Anoa'i]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sika Anoa'i
Context triple: [Ata Johnson, relative, Sika Anoa'i]
  • A. Leati Joseph Anoa'i
    Leati Joseph Anoa'i is an American professional wrestler and former gridiron football player best known worldwide for performing in WWE under the ring name Roman Reigns.
  • B. Afa Anoa'i chosen
    Afa Anoa'i is a Samoan professional wrestling legend, best known as one half of The Wild Samoans tag team and as a trainer and patriarch of the Anoa'i wrestling family.
  • C. Tai Tuivasa
    Tai Tuivasa is an Australian mixed martial artist and fan-favorite UFC heavyweight known for his knockout power and post-fight “shoey” beer celebrations.
  • D. Sione
    Sione is a fictional character played by New Zealand actor Julian Dennison, best known from his comedic and coming-of-age film roles.
  • E. Tomu Sione
    Tomu Sione was a Tuvaluan politician who served as the country's governor-general.
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e766388190aad1039fe0849771 completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.