Triple
T9714003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Wiessee |
E235091
|
entity |
| Predicate | hasMineralSpringType |
P55046
|
FINISHED |
| Object | iodine-rich springs |
—
|
LITERAL 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: iodine-rich springs | Statement: [Bad Wiessee, hasMineralSpringType, iodine-rich springs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMineralSpringType Context triple: [Bad Wiessee, hasMineralSpringType, iodine-rich springs]
-
A.
hasMineralSpringsType
chosen
Indicates that an entity is associated with or characterized by a specific type or category of mineral springs.
-
B.
hasMineralSprings
Indicates that a place or entity possesses or is characterized by the presence of mineral springs.
-
C.
hasHotSpring
Indicates that one entity possesses, contains, or is associated with a hot spring.
-
D.
hasFreshwaterSprings
Indicates that the subject contains or is associated with natural sources of freshwater emerging from the ground.
-
E.
hasNumberOfHotSprings
Indicates the quantity of hot springs associated with a given entity.
- F. None of above.
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_69ca84cd8fa0819090a5e243ceb37003 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e087a1c8190aa62c910f88e8516 |
completed | April 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69cd03bfeca08190924fca43aaa9c10f |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:19 p.m.