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.