Triple

T11457310
Position Surface form Disambiguated ID Type / Status
Subject Dlamini E271562 entity
Predicate hasNotableBearer P458 FINISHED
Object Sjava Dlamini
Sjava Dlamini is a South African musician and actor known for blending Afro-soul, hip-hop, and traditional Zulu influences in his work.
E925683 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: Sjava Dlamini | Statement: [Dlamini, hasNotableBearer, Sjava Dlamini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sjava Dlamini
Context triple: [Dlamini, hasNotableBearer, Sjava Dlamini]
  • A. Dlamin
    Dlamin is the family name of Amala Ratna Zandile Dlamin, better known as the American rapper and singer Doja Cat.
  • B. Ndlela Dlamini
    Ndlela Dlamini is a member of the Mandela-Dlamini family and a descendant of Nelson Mandela through his daughter Zenani Mandela-Dlamini.
  • C. Thamsanqa
    Thamsanqa is a given name of Southern African origin, notably used as the middle name of Trevor Thamsanqa Tutu, the son of Archbishop Desmond Tutu.
  • D. Zindziswa
    Zindziswa is the given first name of Zindzi Mandela, the South African diplomat, poet, and daughter of Nelson Mandela and Winnie Madikizela-Mandela.
  • E. Fundi
    Fundi was an ancient town in central Italy that served as an important settlement of the Volsci people before coming under Roman control.
  • 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: Sjava Dlamini
Triple: [Dlamini, hasNotableBearer, Sjava Dlamini]
Generated description
Sjava Dlamini is a South African musician and actor known for blending Afro-soul, hip-hop, and traditional Zulu influences in his work.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sjava Dlamini
Target entity description: Sjava Dlamini is a South African musician and actor known for blending Afro-soul, hip-hop, and traditional Zulu influences in his work.
  • A. Dlamin
    Dlamin is the family name of Amala Ratna Zandile Dlamin, better known as the American rapper and singer Doja Cat.
  • B. Ndlela Dlamini
    Ndlela Dlamini is a member of the Mandela-Dlamini family and a descendant of Nelson Mandela through his daughter Zenani Mandela-Dlamini.
  • C. Thamsanqa
    Thamsanqa is a given name of Southern African origin, notably used as the middle name of Trevor Thamsanqa Tutu, the son of Archbishop Desmond Tutu.
  • D. Zindziswa
    Zindziswa is the given first name of Zindzi Mandela, the South African diplomat, poet, and daughter of Nelson Mandela and Winnie Madikizela-Mandela.
  • E. Fundi
    Fundi was an ancient town in central Italy that served as an important settlement of the Volsci people before coming under Roman control.
  • 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_69d6aadff8888190a13f253f0d460874 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d81c71b1208190be1d5623d18e0222 completed April 9, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d3e197c881909db2e4e59c61c3c3 completed April 20, 2026, 7:21 a.m.
NEDg Description generation batch_69e5d5cc251081908b85f264940a6545 completed April 20, 2026, 7:29 a.m.
NED2 Entity disambiguation (via description) batch_69e5d924963c8190bfc55ffeb529a499 completed April 20, 2026, 7:43 a.m.
Created at: April 8, 2026, 9:35 p.m.