Triple
T19565542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hochrhein region |
E489571
|
entity |
| Predicate | hasUrbanCenter |
P2106
|
FINISHED |
| Object | Bad Säckingen |
—
|
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: Bad Säckingen | Statement: [Hochrhein region, hasUrbanCenter, Bad Säckingen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Säckingen Context triple: [Hochrhein region, hasUrbanCenter, Bad Säckingen]
-
A.
Bad Säckingen
chosen
Bad Säckingen is a historic spa town in southwestern Germany on the Rhine River, known for its medieval old town and one of the longest covered wooden bridges in Europe.
-
B.
Bad Cannstatt
Bad Cannstatt is a historic district of Stuttgart, Germany, known for its mineral springs, traditional architecture, and the Cannstatter Volksfest beer festival.
-
C.
Bad Dürrheim
Bad Dürrheim is a spa town in southwestern Germany known for its health resorts and saline baths.
-
D.
Bad Wilsnack
Bad Wilsnack is a small spa town in the German state of Brandenburg, known historically as a medieval pilgrimage site.
-
E.
Bad Rappenau
Bad Rappenau is a spa town in the German state of Baden-Württemberg, known for its thermal baths and health resorts.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63f777cf081909312b46ac09bce7c |
completed | April 20, 2026, 3 p.m. |
Created at: April 10, 2026, 1:42 p.m.