Triple
T22150893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonheiden |
E547408
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Keerbergen |
—
|
NE NERFINISHED |
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: Keerbergen | Statement: [Bonheiden, locatedNear, Keerbergen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keerbergen Context triple: [Bonheiden, locatedNear, Keerbergen]
-
A.
Keerbergen
chosen
Keerbergen is a municipality in the Flemish Brabant province of Belgium, known for its residential character and green, wooded surroundings.
-
B.
Kerkrade
Kerkrade is a town in the southeastern Netherlands, near the German border, known for its mining history and the international music festival WMC Kerkrade.
-
C.
Koudekerke
Koudekerke is a village in the Dutch province of Zeeland, located near the North Sea coast on the former island of Walcheren.
-
D.
Kortenaken
Kortenaken is a rural municipality in the Flemish Brabant province of Belgium, known for its agricultural landscape and small village communities.
-
E.
Harelbeke
Harelbeke is a municipality in the Belgian province of West Flanders, known for its historic town center and as a regular host of the E3 Saxo Bank Classic cycling race.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f37dac8190a7cecb12f4271515 |
completed | April 28, 2026, 9:43 p.m. |
Created at: April 16, 2026, 8:33 p.m.