Triple
T37726903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Lary-Soulan |
E940045
|
entity |
| Predicate | skiAreaLocatedIn |
P91152
|
FINISHED |
| Object | Domaine de Saint-Lary |
—
|
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: Domaine de Saint-Lary | Statement: [Saint-Lary-Soulan, skiAreaLocatedIn, Domaine de Saint-Lary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skiAreaLocatedIn Context triple: [Saint-Lary-Soulan, skiAreaLocatedIn, Domaine de Saint-Lary]
-
A.
skiAreaName
Indicates that an entity has a specific name used to identify a ski area.
-
B.
skiResortLocatedIn
chosen
Indicates that a ski resort is situated within or belongs to a specific geographic location or administrative area.
-
C.
skiAreaLinkedTo
Indicates that one ski area is connected or associated with another, such as through shared lifts, trails, passes, or coordinated operations.
-
D.
skiAreaServedBy
Indicates that a ski area is provided with services, access, or support by a specified entity (such as a company, organization, or facility).
-
E.
skiRegion
Indicates that a location is recognized as a ski area or resort where skiing activities take place.
- 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_69f76edefd048190a32212c5c3919531 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaef0cec881908c2742d77d145901 |
completed | May 6, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69fbadf632ec8190b14991c971258307 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.