Triple

T2475757
Position Surface form Disambiguated ID Type / Status
Subject Zenani Mandela-Dlamini E55084 entity
Predicate givenName P17 FINISHED
Object Zenani
Zenani is a South African diplomat and the daughter of Nelson Mandela and Winnie Madikizela-Mandela.
 E270404 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: Zenani | Statement: [Zenani Mandela-Dlamini, givenName, Zenani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zenani
Context triple: [Zenani Mandela-Dlamini, givenName, Zenani]
  • A. Zana
    Zana is a song featured on the album "Legend of the Sun Virgin" by Peruvian-Australian singer-songwriter and producer Gaby Moreno (performing as part of the project).
  • B. Zenia
    Zenia is a central, enigmatic and manipulative figure in Margaret Atwood's novel "The Robber Bride," whose disruptive influence profoundly affects the lives of three other women.
  • C. Nolani
    Nolani are the inhabitants or natives of the city of Nola in southern Italy.
  • D. Anuta
    Anuta is a small, remote Polynesian outlier island in the Solomon Islands known for its dense population, strong communal culture, and well-preserved traditional way of life.
  • E. Nena
    Nena is a German pop singer and actress best known internationally for her 1983 hit song "99 Luftballons."
  • 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: Zenani
Triple: [Zenani Mandela-Dlamini, givenName, Zenani]
Generated description
Zenani is a South African diplomat and the daughter of Nelson Mandela and Winnie Madikizela-Mandela.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zenani
Target entity description: Zenani is a South African diplomat and the daughter of Nelson Mandela and Winnie Madikizela-Mandela.
  • A. Zana
    Zana is a song featured on the album "Legend of the Sun Virgin" by Peruvian-Australian singer-songwriter and producer Gaby Moreno (performing as part of the project).
  • B. Zenia
    Zenia is a central, enigmatic and manipulative figure in Margaret Atwood's novel "The Robber Bride," whose disruptive influence profoundly affects the lives of three other women.
  • C. Nolani
    Nolani are the inhabitants or natives of the city of Nola in southern Italy.
  • D. Anuta
    Anuta is a small, remote Polynesian outlier island in the Solomon Islands known for its dense population, strong communal culture, and well-preserved traditional way of life.
  • E. Nena
    Nena is a German pop singer and actress best known internationally for her 1983 hit song "99 Luftballons."
  • 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_69ab49e279e88190ab10d7248aea9d11 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd14c8c388190bbdc486ffed6899e completed March 7, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69af17ab837881909bf8704acf9598e4 completed March 9, 2026, 6:55 p.m.
NEDg Description generation batch_69af1a8c7784819088be431513d60325 completed March 9, 2026, 7:07 p.m.
NED2 Entity disambiguation (via description) batch_69af1b10738881909b296ecd3ff53c1b completed March 9, 2026, 7:10 p.m.
Created at: March 6, 2026, 9:45 p.m.