Triple
T19481420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matten bei Interlaken |
E487392
|
entity |
| Predicate | hasNeighboringMunicipality |
P224
|
FINISHED |
| Object | Wilderswil |
—
|
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: Wilderswil | Statement: [Matten bei Interlaken, hasNeighboringMunicipality, Wilderswil]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wilderswil Context triple: [Matten bei Interlaken, hasNeighboringMunicipality, Wilderswil]
-
A.
Wilderswil
chosen
Wilderswil is a picturesque Swiss village in the Bernese Oberland, known as a gateway to the Jungfrau region and a base for hiking and mountain excursions.
-
B.
Dallenwil
Dallenwil is a Swiss municipality known for its alpine setting and outdoor recreation opportunities in the canton of Nidwalden.
-
C.
Flaxweiler
Flaxweiler is a small rural commune in eastern Luxembourg known for its agricultural landscape and proximity to the Moselle wine region.
-
D.
Geroldswil
Geroldswil is a municipality in the canton of Zurich in Switzerland, located in the Limmat Valley near the city of Zurich.
-
E.
Reisiswil
Reisiswil is a small rural municipality in the Oberaargau region of the canton of Bern in Switzerland.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e634393b8081909f5e4c38b2f1a9b7 |
completed | April 20, 2026, 2:12 p.m. |
Created at: April 10, 2026, 1:39 p.m.