Triple
T21659989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | canton of Guebwiller |
E534568
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Soultzmatt |
—
|
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: Soultzmatt | Statement: [canton of Guebwiller, contains, Soultzmatt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soultzmatt Context triple: [canton of Guebwiller, contains, Soultzmatt]
-
A.
Soultzmatt
chosen
Soultzmatt is a commune in the Haut-Rhin department of northeastern France, known for its vineyards and mineral springs in the Alsace wine region.
-
B.
Machtolsheim
Machtolsheim is a village in the Alb-Donau district of Baden-Württemberg, Germany, that forms part of the town of Laichingen.
-
C.
Wiedensahl
Wiedensahl is a small village in Lower Saxony, Germany, best known as the birthplace of the humorist and illustrator Wilhelm Busch.
-
D.
Biedenkopf
Biedenkopf is a small historic town in the German state of Hesse, known for its medieval old town and hilltop castle.
-
E.
Hagetmau
Hagetmau is a small town in southwestern France’s Landes department, known for its rural character and traditional Gascon culture.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef6c06844c81909b9c91e02fa4e6e1 |
completed | April 27, 2026, 2 p.m. |
Created at: April 16, 2026, 6:36 p.m.