Triple
T5000548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Volkeraksluizen |
E112360
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Bergen op Zoom |
E77581
|
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: Bergen op Zoom | Statement: [Volkeraksluizen, nearbyCity, Bergen op Zoom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bergen op Zoom Context triple: [Volkeraksluizen, nearbyCity, Bergen op Zoom]
-
A.
Bergen op Zoom
chosen
Bergen op Zoom is a historic city in the Dutch province of North Brabant, known for its medieval center, fortifications, and location near the Scheldt estuary.
-
B.
Blokzijl
Blokzijl is a historic former trading town and harbor in the Dutch province of Overijssel, known for its picturesque canals and well-preserved old center.
-
C.
De Baarsjes
De Baarsjes is a residential neighborhood in Amsterdam, Netherlands, known for its diverse population, early 20th-century architecture, and canalside urban character.
-
D.
De Akkers
De Akkers is a metro station in Spijkenisse, Netherlands, serving as a terminus on the Rotterdam Metro network.
-
E.
Krimpen aan den IJssel
Krimpen aan den IJssel is a Dutch town and municipality situated along the Hollandse IJssel river, forming part of the Rotterdam metropolitan area.
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd72bd90948190bf6ca21237402949 |
completed | March 20, 2026, 4:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be8a3a5a108190a028920b1ae0be7a |
completed | March 21, 2026, 12:08 p.m. |
Created at: March 20, 2026, 1:34 p.m.