Triple
T17898458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waldshut-Tiengen |
E447495
|
entity |
| Predicate | formedByMergerOf |
P77
|
FINISHED |
| Object | Waldshut |
—
|
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: Waldshut | Statement: [Waldshut-Tiengen, formedByMergerOf, Waldshut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waldshut Context triple: [Waldshut-Tiengen, formedByMergerOf, Waldshut]
-
A.
Waldshut-Tiengen
chosen
Waldshut-Tiengen is a town in southwestern Germany near the Swiss border, formed by the merger of Waldshut and Tiengen and known for its historic old town and Rhine River setting.
-
B.
Wiesloch
Wiesloch is a town in the Rhine-Neckar district of Baden-Württemberg, Germany, known for its historical center and role as a regional commercial hub.
-
C.
Eschau
Eschau is a small commune in northeastern France located near Strasbourg in the Grand Est region.
-
D.
Bochingen
Bochingen is a village and district of the town Oberndorf am Neckar in the state of Baden-Württemberg in southwestern Germany.
-
E.
Waltershof
Waltershof is an industrial and port district of Hamburg, Germany, located within the borough of Hamburg-Mitte.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d8122b481909992356f3f575858 |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:19 a.m.