Triple
T35212666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruinaulta |
E1016728
|
entity |
| Predicate | hasScenicTrain |
P159354
|
FINISHED |
| Object | Ruinaulta-Express |
—
|
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: Ruinaulta-Express | Statement: [Ruinaulta, hasScenicTrain, Ruinaulta-Express]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScenicTrain Context triple: [Ruinaulta, hasScenicTrain, Ruinaulta-Express]
-
A.
hasScenicPassNearby
Indicates that a location is situated close to a notable scenic pass, such as a mountain or landscape viewpoint route.
-
B.
isTouristRailway
chosen
Indicates that a railway is primarily operated for tourism or leisure purposes rather than as a regular public transport service.
-
C.
hasScenicRoutes
Indicates that one location, path, or area offers routes that are visually attractive or notable for their natural or aesthetic scenery.
-
D.
hasMountainRailwayConnectionTo
Indicates that there is a railway line specifically adapted for mountainous terrain that connects one location to another.
-
E.
hasScenicSections
Indicates that a route, path, or area contains segments that are visually attractive or offer notable scenic views.
- 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_69f76ddf549c8190869d0af076fd2c28 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd474b7e788190a9bb9b542d878f60 |
completed | May 8, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69fd46d8b2f0819099d92d72c902f60e |
completed | May 8, 2026, 2:13 a.m. |
Created at: May 3, 2026, 4:02 p.m.