Triple
T16482015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamina thermal spring |
E400342
|
entity |
| Predicate | hasAccessPoint |
P1985
|
FINISHED |
| Object | Bad Ragaz |
E93233
|
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: Bad Ragaz | Statement: [Tamina thermal spring, hasAccessPoint, Bad Ragaz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Ragaz Context triple: [Tamina thermal spring, hasAccessPoint, Bad Ragaz]
-
A.
Bad Ragaz
chosen
Bad Ragaz is a Swiss spa and resort town in the canton of St. Gallen, renowned for its thermal baths and alpine setting.
-
B.
Bad Saarow
Bad Saarow is a German spa town in Brandenburg known for its thermal baths and lakeside setting on the Scharmützelsee.
-
C.
Bad Grönenbach
Bad Grönenbach is a spa town in the Bavarian Allgäu region of southern Germany, known for its health resorts and picturesque rural surroundings.
-
D.
Bad Rodach
Bad Rodach is a small spa town in northern Bavaria, Germany, known for its thermal baths and historic Franconian charm.
-
E.
Bad Bibra
Bad Bibra is a small spa town in the Burgenlandkreis district of Saxony-Anhalt in central Germany, known for its rural setting and historical bathing tradition.
- 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_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e03643881908b16ddb9004af5d0 |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00607aafa48190929250a879c602ca |
completed | May 10, 2026, 10:39 a.m. |
Created at: April 10, 2026, 5:13 a.m.