Triple
T13166414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evian |
E312860
|
entity |
| Predicate | sourceFeature |
P409
|
FINISHED |
| Object | springs near Évian-les-Bains |
—
|
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: springs near Évian-les-Bains | Statement: [Evian, sourceFeature, springs near Évian-les-Bains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceFeature Context triple: [Evian, sourceFeature, springs near Évian-les-Bains]
-
A.
originalFeature
Indicates that one entity is the initial or source feature from which another feature is derived, modified, or referenced.
-
B.
source
chosen
Indicates that something originates from, is derived from, or is provided by a particular entity or location.
-
C.
targetFeature
Indicates that one entity is the specific feature, attribute, or characteristic that another entity is directed toward, focused on, or intended to affect.
-
D.
sourceCategory
Indicates the classification or type from which something originates or is derived.
-
E.
baseFeature
Indicates that one entity serves as the fundamental or primary feature upon which another entity is built or defined.
- 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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bbd1d088190b7c69f37fc6eeb64 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:13 p.m.