Triple

T21391346
Position Surface form Disambiguated ID Type / Status
Subject Middelburg E527656 entity
Predicate near P350 FINISHED
Object Witbank 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: Witbank | Statement: [Middelburg, near, Witbank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Witbank
Context triple: [Middelburg, near, Witbank]
  • A. Witbank chosen
    Witbank is a South African coal-mining city in Mpumalanga province, now officially known as Emalahleni.
  • B. Rustenburg
    Rustenburg is a city in South Africa’s North West Province known for its mining industry and as one of the venues for the 2010 FIFA World Cup.
  • C. Randburg
    Randburg is a residential and commercial suburb in the north of Johannesburg, South Africa, known for its shopping centers, business districts, and leafy neighborhoods.
  • D. Bloemfontein
    Bloemfontein is a major South African city known as the seat of the country’s highest courts and one of its three national capitals.
  • E. Grahamstown
    Grahamstown is a historic university town in South Africa, renowned for its colonial-era architecture and the annual National Arts Festival.
  • 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b113690c81909c0a378fddba5d3a completed April 22, 2026, 11:29 a.m.
Created at: April 16, 2026, 5:13 p.m.