Triple

T334856
Position Surface form Disambiguated ID Type / Status
Subject Koos de la Rey E6702 entity
Predicate nickname P55 FINISHED
Object Koos
Koos is the commonly used nickname of Koos de la Rey, a prominent Boer general and political figure from South African history.
E42621 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: Koos | Statement: [Koos de la Rey, nickname, Koos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Koos
Context triple: [Koos de la Rey, nickname, Koos]
  • A. De Croo
    De Croo is a Belgian political family name most prominently associated with Alexander De Croo, the Prime Minister of Belgium.
  • B. Buitenkaag
    Buitenkaag is a small village in the Dutch province of North Holland, situated in the municipality of Haarlemmermeer near the Kagerplassen lake area.
  • C. Klecko
    Klecko is the surname of former American football defensive lineman Joe Klecko, best known for his standout career with the New York Jets as part of the “New York Sack Exchange.”
  • D. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • E. Volkerak
    Volkerak is a lake and former estuarine channel in the southwestern Netherlands that forms part of the country’s major Rhine–Meuse–Scheldt waterway system.
  • 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: Koos
Triple: [Koos de la Rey, nickname, Koos]
Generated description
Koos is the commonly used nickname of Koos de la Rey, a prominent Boer general and political figure from South African history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Koos
Target entity description: Koos is the commonly used nickname of Koos de la Rey, a prominent Boer general and political figure from South African history.
  • A. De Croo
    De Croo is a Belgian political family name most prominently associated with Alexander De Croo, the Prime Minister of Belgium.
  • B. Buitenkaag
    Buitenkaag is a small village in the Dutch province of North Holland, situated in the municipality of Haarlemmermeer near the Kagerplassen lake area.
  • C. Klecko
    Klecko is the surname of former American football defensive lineman Joe Klecko, best known for his standout career with the New York Jets as part of the “New York Sack Exchange.”
  • D. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • E. Volkerak
    Volkerak is a lake and former estuarine channel in the southwestern Netherlands that forms part of the country’s major Rhine–Meuse–Scheldt waterway system.
  • 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_69a2e79434908190a9d5afe415153ad9 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2eac641708190b85fa21368e5de8e completed Feb. 28, 2026, 1:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3d247650481909006cc27bfa385e3 completed March 1, 2026, 5:44 a.m.
NEDg Description generation batch_69a3d2d8aa64819095cdee306bec77ec completed March 1, 2026, 5:47 a.m.
NED2 Entity disambiguation (via description) batch_69a3d370d200819089eaf114357a8ca3 completed March 1, 2026, 5:49 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.