Triple

T2821302
Position Surface form Disambiguated ID Type / Status
Subject Makaziwe Mandela E54815 entity
Predicate name P16 FINISHED
Object Makaziwe Mandela E54815 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: Makaziwe Mandela | Statement: [Makaziwe Mandela, name, Makaziwe Mandela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Makaziwe Mandela
Context triple: [Makaziwe Mandela, name, Makaziwe Mandela]
  • A. Makaziwe Mandela chosen
    Makaziwe Mandela is a South African businesswoman and academic, best known as the daughter of anti-apartheid icon and former president Nelson Mandela.
  • B. Ndaba Mandela
    Ndaba Mandela is a South African author, entrepreneur, and anti-HIV/AIDS activist, known as the grandson of Nelson Mandela and for his work promoting youth leadership and African development.
  • C. Zindzi Mandela
    Zindzi Mandela was a South African diplomat, poet, and anti-apartheid activist, best known as the daughter of Nelson and Winnie Mandela and for her outspoken role during her father's imprisonment.
  • D. Zondi Mandela
    Zondi Mandela was the wife of Makgatho Mandela and a member of South Africa’s prominent Mandela family.
  • E. Thembekile Mandela
    Thembekile Mandela was one of Nelson Mandela and Evelyn Mase’s sons, who died in a car accident in 1969.
  • 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_69ab49e100c0819082a40cb797383243 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde6e85008190a08eb2bf8e393e7e completed March 7, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d6b1ebc8190ae54d560abb5e612 completed March 10, 2026, 1:32 p.m.
Created at: March 6, 2026, 9:59 p.m.