Triple

T7662402
Position Surface form Disambiguated ID Type / Status
Subject Bridgette Radebe E173537 entity
Predicate spouse P13 FINISHED
Object Jeff Radebe E680632 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: Jeff Radebe | Statement: [Bridgette Radebe, spouse, Jeff Radebe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeff Radebe
Context triple: [Bridgette Radebe, spouse, Jeff Radebe]
  • A. Jeff Radebe chosen
    Jeff Radebe is a South African politician who has held several key ministerial positions in the post-apartheid government, including serving as Minister of Justice and Constitutional Development.
  • B. Lucas Radebe
    Lucas Radebe is a retired South African footballer best known as a long-serving defender and captain for Leeds United and the South African national team, Bafana Bafana.
  • C. Darrell Roodt
    Darrell Roodt is a South African film director known for socially conscious dramas that often explore apartheid and its legacy, including the acclaimed musical film "Sarafina!".
  • D. Stefan Pienaar
    Stefan Pienaar is known as one of the sons of former South African rugby union captain Francois Pienaar.
  • E. Schalk van der Merwe
    Schalk van der Merwe was a South African professional tennis player active primarily in the late 1970s and early 1980s.
  • 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_69c69955517c819085bc715b96d304d2 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701a74a2c81909f78ab2de7ce807c completed March 27, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7b5f1a48190b409230029c96fa8 completed March 29, 2026, 6:33 a.m.
Created at: March 27, 2026, 3:59 p.m.