Triple

T21749972
Position Surface form Disambiguated ID Type / Status
Subject Aaron Mokoena E536888 entity
Predicate fullName P16 FINISHED
Object Teboho Aaron Mokoena 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: Teboho Aaron Mokoena | Statement: [Aaron Mokoena, fullName, Teboho Aaron Mokoena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teboho Aaron Mokoena
Context triple: [Aaron Mokoena, fullName, Teboho Aaron Mokoena]
  • A. Douglas Mohlabane
    Douglas Mohlabane is the South African father of American soul and R&B singer Goapele.
  • B. Skhuthazo Winston Khanyile
    Skhuthazo Winston Khanyile is a South African individual best known as the husband of acclaimed actress Leleti Khumalo.
  • C. Lawrence Mbatha
    Lawrence Mbatha is a senior South African military officer who serves as the head of the South African Army.
  • D. Patrick Mofokeng
    Patrick Mofokeng is a South African actor known for his roles in film and television, particularly in politically themed dramas.
  • E. Aaron Mokoena chosen
    Aaron Mokoena is a South African former professional footballer and defender who captained the national team, Bafana Bafana, including at the 2010 FIFA World Cup.
  • 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_69e0c46eab808190b848242d63a17c47 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01a79fb74819098a247c4f31598a8 completed April 28, 2026, 2:24 a.m.
Created at: April 16, 2026, 6:50 p.m.