Triple

T22313265
Position Surface form Disambiguated ID Type / Status
Subject Polokwane Game Reserve E551577 entity
Predicate locatedIn P40 FINISHED
Object Polokwane 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: Polokwane | Statement: [Polokwane Game Reserve, locatedIn, Polokwane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Polokwane
Context triple: [Polokwane Game Reserve, locatedIn, Polokwane]
  • A. Polokwane chosen
    Polokwane is a city in South Africa’s Limpopo province that served as one of the venues for matches during the 2010 FIFA World Cup.
  • B. Mthatha
    Mthatha is a town in South Africa known as a regional economic and administrative center in the Eastern Cape and as the birthplace of Nelson Mandela.
  • C. Mbombela
    Mbombela is a city in northeastern South Africa that serves as a regional economic and administrative hub near the border with Mozambique.
  • D. Mogoditshane
    Mogoditshane is a rapidly growing suburban township located just outside Botswana’s capital, Gaborone.
  • E. Mogale City
    Mogale City is a local municipality in Gauteng, South Africa, that includes the town of Krugersdorp and surrounding areas on the West Rand.
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15750f76c81909d6f788928f503f1 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:42 p.m.