Triple

T2821303
Position Surface form Disambiguated ID Type / Status
Subject Makaziwe Mandela E54815 entity
Predicate givenName P17 FINISHED
Object Makaziwe
Makaziwe is a South African academic and businesswoman best known as the daughter of Nelson Mandela.
 E301782 NE FINISHED

How this triple was built (4 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 | Statement: [Makaziwe Mandela, givenName, Makaziwe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Makaziwe
Context triple: [Makaziwe Mandela, givenName, Makaziwe]
  • A. Madikizela
    Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
  • B. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • C. Maphelane
    Maphelane is a coastal nature reserve in South Africa known for its high vegetated dunes, rich birdlife, and diverse estuarine and marine habitats within the iSimangaliso Wetland Park.
  • D. Makhuwa
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • E. Zindziswa
    Zindziswa is the given first name of Zindzi Mandela, the South African diplomat, poet, and daughter of Nelson Mandela and Winnie Madikizela-Mandela.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Makaziwe
Triple: [Makaziwe Mandela, givenName, Makaziwe]
Generated description
Makaziwe is a South African academic and businesswoman best known as the daughter of Nelson Mandela.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Makaziwe
Target entity description: Makaziwe is a South African academic and businesswoman best known as the daughter of Nelson Mandela.
  • A. Madikizela
    Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
  • B. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • C. Maphelane
    Maphelane is a coastal nature reserve in South Africa known for its high vegetated dunes, rich birdlife, and diverse estuarine and marine habitats within the iSimangaliso Wetland Park.
  • D. Makhuwa
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • E. Zindziswa
    Zindziswa is the given first name of Zindzi Mandela, the South African diplomat, poet, and daughter of Nelson Mandela and Winnie Madikizela-Mandela.
  • F. None of above. chosen

Provenance (5 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_69afcea809e48190b22f25a3c8c1acdd completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afcff5af4c819082b2cf316723440a completed March 10, 2026, 8:01 a.m.
NED2 Entity disambiguation (via description) batch_69afd07923fc819097051017d3e2b5da completed March 10, 2026, 8:04 a.m.
Created at: March 6, 2026, 9:59 p.m.