Triple

T2482057
Position Surface form Disambiguated ID Type / Status
Subject Zindzi Mandela E55839 entity
Predicate placeOfBirth P1 FINISHED
Object Soweto E31807 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: Soweto | Statement: [Zindzi Mandela, placeOfBirth, Soweto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soweto
Context triple: [Zindzi Mandela, placeOfBirth, Soweto]
  • A. Soweto chosen
    Soweto is a historically significant township in Johannesburg, South Africa, known for its central role in the struggle against apartheid and its rich urban culture.
  • B. Gladysvale
    Gladysvale is a fossil-bearing cave site in South Africa known for its important hominin and animal fossil discoveries within the Cradle of Humankind World Heritage area.
  • C. Mamelodi
    Mamelodi is a township in the northeastern part of Pretoria, South Africa, known for its vibrant football culture and as the home of Mamelodi Sundowns F.C.
  • D. Johannesburg, South Africa
    Johannesburg, South Africa is the country’s largest city and economic hub, known for its role in the gold mining industry and as a major urban center in Gauteng province.
  • E. Midrand
    Midrand is a rapidly growing commercial and residential area in South Africa strategically located between Johannesburg and Pretoria in the province of Gauteng.
  • 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_69ab49e670a88190b928e08302381710 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd163378481908b75f2f5de0e89c6 completed March 7, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f8c02188190a7cf3e0531a66683 completed March 9, 2026, 7:29 p.m.
Created at: March 6, 2026, 9:45 p.m.