Triple
T11626679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | County of Guelders |
E276287
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Geldern |
E527096
|
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: Geldern | Statement: [County of Guelders, capital, Geldern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geldern Context triple: [County of Guelders, capital, Geldern]
-
A.
Geldern
chosen
Geldern is a historic town in western Germany, notable as the namesake and former center of the medieval Duchy of Guelders.
-
B.
Zutphen
Zutphen is a historic city in the eastern Netherlands known for its well-preserved medieval center and location along the river IJssel.
-
C.
Zundert
Zundert is a municipality and town in the southern Netherlands, known as the birthplace of painter Vincent van Gogh and for hosting one of the world's largest flower parades.
-
D.
Culemborg
Culemborg is a historic town in the Dutch province of Gelderland, known for its medieval center and role in the early Dutch colonial era.
-
E.
Woerden
Woerden is a historic Dutch city and municipality in the central Netherlands, known for its medieval fortifications and traditional cheese market.
- 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_69d6aafa51148190ab84940694c00235 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a1259cd08190a75eeacb5e39b858 |
completed | April 10, 2026, 7:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c78f36d88190a39f407c5d8dbc0d |
completed | May 10, 2026, 5:59 p.m. |
Created at: April 8, 2026, 9:39 p.m.