Triple
T27819398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Peter spring |
E702770
|
entity |
| Predicate | hasWaterOrigin |
P12617
|
FINISHED |
| Object | alpine aquifer |
—
|
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: alpine aquifer | Statement: [St. Peter spring, hasWaterOrigin, alpine aquifer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWaterOrigin Context triple: [St. Peter spring, hasWaterOrigin, alpine aquifer]
-
A.
hasWaterMassOrigin
Indicates that something originates from, or is derived from, a particular body or mass of water.
-
B.
waterOrigin
chosen
Indicates the source or starting location from which the water originates or is supplied.
-
C.
hasHydronymOrigin
Indicates that something derives its name from a body of water or hydrological feature.
-
D.
hasWaterResourceRole
Indicates that an entity participates in a water-related resource context with a specified functional role (e.g., source, user, manager, or regulator of water resources).
-
E.
hasHeadwatersIn
Indicates that the source or origin of a river, stream, or similar watercourse is located within a specified geographic area or feature.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 5:47 p.m.