Triple
T12055624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Churfirsten |
E287033
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Walenstadt |
E960890
|
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: Walenstadt | Statement: [Churfirsten, nearestTown, Walenstadt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walenstadt Context triple: [Churfirsten, nearestTown, Walenstadt]
-
A.
Walenstadt
chosen
Walenstadt is a Swiss town on the shores of Lake Walen in the canton of St. Gallen, known for its scenic alpine surroundings and outdoor recreation opportunities.
-
B.
Schorisse
Schorisse is a village in East Flanders, Belgium, that now forms part of the municipality of Maarkedal.
-
C.
Eysins
Eysins is a small municipality in the canton of Vaud in western Switzerland, situated near the town of Nyon and close to Lake Geneva.
-
D.
Reichenau
Reichenau is a German municipality best known for its UNESCO-listed monastic island on Lake Constance, renowned for its medieval abbey and cultural heritage.
-
E.
Lindau
Lindau is a historic Bavarian town in southern Germany located on an island in Lake Constance near the borders with Austria and Switzerland.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90425258c8190ba7b3b837c439253 |
completed | April 10, 2026, 2:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e3ee53c81909c2e4620a12a46da |
completed | May 2, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:47 p.m.