Triple

T1226271
Position Surface form Disambiguated ID Type / Status
Subject Winnie Mandela E26333 entity
Predicate familyName P18 FINISHED
Object Madikizela
Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
E150542 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: Madikizela | Statement: [Winnie Mandela, familyName, Madikizela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madikizela
Context triple: [Winnie Mandela, familyName, Madikizela]
  • A. 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.
  • 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. Makhuwa
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • D. Bongi
    Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
  • E. Mafadi
    Mafadi is a prominent mountain peak on the border of South Africa and Lesotho, renowned as the highest point in South Africa and a popular destination for serious hikers and mountaineers.
  • 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: Madikizela
Triple: [Winnie Mandela, familyName, Madikizela]
Generated description
Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Madikizela
Target entity description: Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
  • A. 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.
  • 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. Makhuwa
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • D. Bongi
    Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
  • E. Mafadi
    Mafadi is a prominent mountain peak on the border of South Africa and Lesotho, renowned as the highest point in South Africa and a popular destination for serious hikers and mountaineers.
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be39908481908cca21aaf0828415 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69acbadec0808190a3b43e757e1ddeae completed March 7, 2026, 11:55 p.m.
NEDg Description generation batch_69acbb5ee684819083f5309dc9771c3a completed March 7, 2026, 11:57 p.m.
NED2 Entity disambiguation (via description) batch_69acbbfee7e88190b216beef1c862f64 completed March 7, 2026, 11:59 p.m.
Created at: March 1, 2026, 7:47 p.m.