Triple

T11176823
Position Surface form Disambiguated ID Type / Status
Subject Siya Kolisi E264432 entity
Predicate hasChild P369 FINISHED
Object Kezi Kolisi E911521 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: Kezi Kolisi | Statement: [Siya Kolisi, hasChild, Kezi Kolisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kezi Kolisi
Context triple: [Siya Kolisi, hasChild, Kezi Kolisi]
  • A. Siya Kolisi
    Siya Kolisi is a South African rugby union flanker who became the first black captain of the Springboks and led them to Rugby World Cup titles in 2019 and 2023.
  • B. Nicholas Kolisi chosen
    Nicholas Kolisi is one of the children of South African rugby union star and Springboks captain Siya Kolisi.
  • C. Heyneke Meyer
    Heyneke Meyer is a South African rugby union coach best known for coaching the national Springboks and leading the Bulls to multiple Super Rugby titles.
  • D. Rassie Erasmus
    Rassie Erasmus is a South African rugby coach and former player best known for leading the Springboks to the 2019 Rugby World Cup title and revolutionizing their tactical approach.
  • E. Dan Pienaar
    Dan Pienaar was a prominent South African Army general best known for his leadership of South African forces during key campaigns of the Second World War, particularly in North Africa.
  • 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8987e1081909b28a0bdb866beae completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4acf79b748190b117355f60c8c015 completed April 19, 2026, 10:22 a.m.
Created at: April 8, 2026, 9:29 p.m.