Triple
T1962685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koos de la Rey |
E42621
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Koos |
E42621
|
NE FINISHED |
How this triple was built (2 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, givenName, Koos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koos Context triple: [Koos de la Rey, givenName, Koos]
-
A.
Koos
chosen
Koos is the commonly used nickname of Koos de la Rey, a prominent Boer general and political figure from South African history.
-
B.
Boskoop
Boskoop is a Dutch town historically renowned as a major center of tree and nursery cultivation.
-
C.
Ruurlo
Ruurlo is a village in the Dutch province of Gelderland, known for its historic estates and rural character.
-
D.
Korte Niezel
Korte Niezel is a narrow street in Amsterdam’s historic city center, located in the Red Light District near the Oudezijds Voorburgwal canal.
-
E.
Van der Madeweg
Van der Madeweg is a metro station in Amsterdam that serves as a stop on the city's rapid transit network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a88711151c8190940b2572095059d7 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3ac31a08190abaecac8badc52c7 |
completed | March 7, 2026, 5:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adfbd133908190add1c78d91a813ef |
completed | March 8, 2026, 10:44 p.m. |
Created at: March 4, 2026, 7:36 p.m.