Triple

T21969607
Position Surface form Disambiguated ID Type / Status
Subject Andries Odendaal E542551 entity
Predicate workLocation P7 FINISHED
Object South Africa 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: South Africa | Statement: [Andries Odendaal, workLocation, South Africa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: South Africa
Context triple: [Andries Odendaal, workLocation, South Africa]
  • A. South Africa chosen
    South Africa is a country at the southern tip of the African continent, known for its cultural and linguistic diversity, complex history of apartheid and democratic transition, and significant economic and political influence in the region.
  • B. Transkei, South Africa
    Transkei, South Africa was a former bantustan in the southeastern part of the country, historically designated for Xhosa-speaking people during the apartheid era.
  • C. Jong Suid-Afrika
    Jong Suid-Afrika was the original name of the Afrikaner Broederbond, a secretive and influential Afrikaner nationalist organization in South Africa.
  • D. Kwaluseni
    Kwaluseni is a town in Eswatini known primarily as the main campus site of the University of Eswatini.
  • E. Tiszanána
    Tiszanána is a village in northern Hungary known for its proximity to the Tisza River and recreational areas around Lake Tisza.
  • 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1245d50d08190a4bf93139daa77eb completed April 28, 2026, 9:19 p.m.
Created at: April 16, 2026, 8:02 p.m.