Triple

T7998737
Position Surface form Disambiguated ID Type / Status
Subject Potgieter E186191 entity
Predicate hasNotableBearer P458 FINISHED
Object Deon Potgieter
Deon Potgieter is a South African sports journalist, commentator, and author best known for his coverage of boxing and combat sports.
E707972 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: Deon Potgieter | Statement: [Potgieter, hasNotableBearer, Deon Potgieter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deon Potgieter
Context triple: [Potgieter, hasNotableBearer, Deon Potgieter]
  • A. Riaan Louw
    Riaan Louw is a person notable enough to be recognized as a significant bearer of the surname Louw.
  • B. Marnus Potgieter
    Marnus Potgieter is a South African cricketer known for playing domestic professional cricket.
  • C. Handré Pollard
    Handré Pollard is a South African rugby union fly-half renowned for his pivotal role in the Springboks’ World Cup–winning campaigns and his accurate goal-kicking under pressure.
  • D. J. P. Snyman
    J. P. Snyman was a Boer military leader best known for directing the besieging forces against the British-held town of Mafeking during the Second Boer War.
  • E. Jaco Louw
    Jaco Louw is a notable individual bearing the Afrikaans surname Louw, recognized within contexts where the name has particular cultural or public significance.
  • 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: Deon Potgieter
Triple: [Potgieter, hasNotableBearer, Deon Potgieter]
Generated description
Deon Potgieter is a South African sports journalist, commentator, and author best known for his coverage of boxing and combat sports.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Deon Potgieter
Target entity description: Deon Potgieter is a South African sports journalist, commentator, and author best known for his coverage of boxing and combat sports.
  • A. Riaan Louw
    Riaan Louw is a person notable enough to be recognized as a significant bearer of the surname Louw.
  • B. Marnus Potgieter
    Marnus Potgieter is a South African cricketer known for playing domestic professional cricket.
  • C. Handré Pollard
    Handré Pollard is a South African rugby union fly-half renowned for his pivotal role in the Springboks’ World Cup–winning campaigns and his accurate goal-kicking under pressure.
  • D. J. P. Snyman
    J. P. Snyman was a Boer military leader best known for directing the besieging forces against the British-held town of Mafeking during the Second Boer War.
  • E. Jaco Louw
    Jaco Louw is a notable individual bearing the Afrikaans surname Louw, recognized within contexts where the name has particular cultural or public significance.
  • 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c9a12788190a5607a538f4e07c1 completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56910dd4819084ffe3350f15d95d completed March 31, 2026, 11:19 p.m.
NEDg Description generation batch_69cc58ecd0608190ab0880992bc203fb completed March 31, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_69cc5cb2963c81908a8dfbb1f84845bc completed March 31, 2026, 11:45 p.m.
Created at: March 30, 2026, 5:17 p.m.