Triple

T14637762
Position Surface form Disambiguated ID Type / Status
Subject 99 Homes E343649 entity
Predicate editedBy P1954 FINISHED
Object Pieter Viljoen
Pieter Viljoen is a film editor known for his work on the drama film "99 Homes."
E1110005 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: Pieter Viljoen | Statement: [99 Homes, editedBy, Pieter Viljoen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pieter Viljoen
Context triple: [99 Homes, editedBy, Pieter Viljoen]
  • A. Christo Louw
    Christo Louw is a South African individual notable enough to be recognized as a prominent bearer of the surname Louw.
  • B. Ruan Potgieter
    Ruan Potgieter is a South African rugby union player known for his role as a prop.
  • C. Tjaart Potgieter
    Tjaart Potgieter is a person notable enough to be recognized as a bearer of the Potgieter surname.
  • D. André Louw
    André Louw is a relatively obscure individual whose name is notably associated with the surname Louw.
  • E. Joost van der Westhuizen
    Joost van der Westhuizen was a legendary South African scrum-half renowned for his pivotal role in the Springboks’ 1995 Rugby World Cup victory and his status as one of the greatest players in rugby union history.
  • 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: Pieter Viljoen
Triple: [99 Homes, editedBy, Pieter Viljoen]
Generated description
Pieter Viljoen is a film editor known for his work on the drama film "99 Homes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pieter Viljoen
Target entity description: Pieter Viljoen is a film editor known for his work on the drama film "99 Homes."
  • A. Christo Louw
    Christo Louw is a South African individual notable enough to be recognized as a prominent bearer of the surname Louw.
  • B. Ruan Potgieter
    Ruan Potgieter is a South African rugby union player known for his role as a prop.
  • C. Tjaart Potgieter
    Tjaart Potgieter is a person notable enough to be recognized as a bearer of the Potgieter surname.
  • D. André Louw
    André Louw is a relatively obscure individual whose name is notably associated with the surname Louw.
  • E. Joost van der Westhuizen
    Joost van der Westhuizen was a legendary South African scrum-half renowned for his pivotal role in the Springboks’ 1995 Rugby World Cup victory and his status as one of the greatest players in rugby union history.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4aca6448190adf1042dfbfef716 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda934ec3c81909eb3c3a54260436b completed May 8, 2026, 9:13 a.m.
NEDg Description generation batch_69fdb1ad32a4819088e5831f3d74ea4e completed May 8, 2026, 9:49 a.m.
NED2 Entity disambiguation (via description) batch_69fdb316479c81909343196bb89e5e57 completed May 8, 2026, 9:55 a.m.
Created at: April 10, 2026, 1:26 a.m.