Triple
T36900420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canillo |
E912015
|
entity |
| Predicate | hasSkiResortArea |
P1981
|
FINISHED |
| Object |
Soldeu-El Tarter
Soldeu-El Tarter is a major ski resort area in Andorra, known for its extensive slopes, modern facilities, and role as part of the Grandvalira ski domain.
|
E2203565
|
NE FINISHED |
How this triple was built (3 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: Soldeu-El Tarter | Statement: [Canillo, hasSkiResortArea, Soldeu-El Tarter]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Soldeu-El Tarter Triple: [Canillo, hasSkiResortArea, Soldeu-El Tarter]
Generated description
Soldeu-El Tarter is a major ski resort area in Andorra, known for its extensive slopes, modern facilities, and role as part of the Grandvalira ski domain.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSkiResortArea Context triple: [Canillo, hasSkiResortArea, Soldeu-El Tarter]
-
A.
hasSkiResortType
Indicates that an entity is associated with, or classified by, a specific type or category of ski resort.
-
B.
hasSkiAreaAccess
Indicates that an entity provides direct access to, or is directly connected with, a ski area or ski facilities.
-
C.
hasSkiResortFeature
Indicates that a ski resort possesses or offers a specific feature, amenity, or characteristic.
-
D.
hasSkiPassArea
Indicates that an entity’s ski pass grants access to a specific ski area or region.
-
E.
hasSkiResortNearby
chosen
Indicates that one location is situated close enough to another location that it can be considered to have a ski resort in its vicinity.
- F. None of above.
Provenance (6 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_69f76e841b54819097e7fa768bbc70b2 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd943fdc81909e18d81b6b5ff967 |
completed | May 5, 2026, 2:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3dfafc3eac819086e7ab4cd819b7ca |
completed | June 26, 2026, 4:07 a.m. |
| NEDg | Description generation | batch_6a3dff7742d08190adb05eac0e35e509 |
completed | June 26, 2026, 4:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3e09fbf0f481908ca9d7890430b16b |
completed | June 26, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.