Triple

T21629850
Position Surface form Disambiguated ID Type / Status
Subject Kaizer Motaung E533800 entity
Predicate givenName P17 FINISHED
Object Kaizer
Kaizer is a South African football executive and former player best known as the founder and chairman of Kaizer Chiefs Football Club.
 E1493513 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: Kaizer | Statement: [Kaizer Motaung, givenName, Kaizer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kaizer
Context triple: [Kaizer Motaung, givenName, Kaizer]
  • A. Keizer
    Keizer is a Dutch surname most notably associated with Piet Keizer, a celebrated footballer who starred for Ajax and the Netherlands in the 1960s and 1970s.
  • B. Harkes
    Harkes is a surname most notably associated with John Harkes, a former American soccer player and captain of the U.S. national team.
  • C. Kaka
    Kaka is the popular nickname of Rajesh Khanna, the legendary Indian film actor often hailed as Bollywood’s first superstar.
  • D. Kaka
    Kaka is a small town in Turkmenistan known as an administrative and transport hub within the Ahal Region.
  • E. Zahawi
    Zahawi is the surname of Nadhim Zahawi, a British Conservative politician and former Chancellor of the Exchequer.
  • 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: Kaizer
Triple: [Kaizer Motaung, givenName, Kaizer]
Generated description
Kaizer is a South African football executive and former player best known as the founder and chairman of Kaizer Chiefs Football Club.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kaizer
Target entity description: Kaizer is a South African football executive and former player best known as the founder and chairman of Kaizer Chiefs Football Club.
  • A. Keizer
    Keizer is a Dutch surname most notably associated with Piet Keizer, a celebrated footballer who starred for Ajax and the Netherlands in the 1960s and 1970s.
  • B. Harkes
    Harkes is a surname most notably associated with John Harkes, a former American soccer player and captain of the U.S. national team.
  • C. Kaka
    Kaka is the popular nickname of Rajesh Khanna, the legendary Indian film actor often hailed as Bollywood’s first superstar.
  • D. Kaka
    Kaka is a small town in Turkmenistan known as an administrative and transport hub within the Ahal Region.
  • E. Zahawi
    Zahawi is the surname of Nadhim Zahawi, a British Conservative politician and former Chancellor of the Exchequer.
  • 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef5215ae3c81909e6dedba23822970 completed April 27, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a0f97ba188190b00ddfbbeee22499 completed May 17, 2026, 6:57 p.m.
NEDg Description generation batch_6a0a1020e67c8190a6faf7e8e458d48e completed May 17, 2026, 6:59 p.m.
NED2 Entity disambiguation (via description) batch_6a0a10ac13288190a1fbf21fa67a4ed2 completed May 17, 2026, 7:02 p.m.
Created at: April 16, 2026, 6:34 p.m.