Triple
T16337682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Åreskutan |
E396716
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object |
Tegefjäll
Tegefjäll is a small ski resort settlement in the Åre ski area of Jämtland, Sweden.
|
E1210933
|
NE FINISHED |
How this triple was built (4 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: Tegefjäll | Statement: [Åreskutan, hasNearbySettlement, Tegefjäll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tegefjäll Context triple: [Åreskutan, hasNearbySettlement, Tegefjäll]
-
A.
Helagsfjället
Helagsfjället is a prominent mountain massif in Sweden known for its glacier, popular hiking trails, and rich alpine scenery.
-
B.
Sonfjället
Sonfjället is a prominent mountain and national park in central Sweden, known for its rounded peak, extensive forests, and rich wildlife including one of the country’s oldest bear populations.
-
C.
Ramnefjellet
Ramnefjellet is a mountain in Norway best known for the massive rockslides in the early 20th century that caused catastrophic tsunamis in the nearby lake Lovatnet.
-
D.
Heilefjellet
Heilefjellet is a mountain located in the coastal municipality of Bremanger in Vestland county, western Norway.
-
E.
Råðdjärum
Råðdjärum is the Elfdalian-language name for the Elfdalian Language Council, an organization dedicated to preserving and promoting the Elfdalian language.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Tegefjäll Triple: [Åreskutan, hasNearbySettlement, Tegefjäll]
Generated description
Tegefjäll is a small ski resort settlement in the Åre ski area of Jämtland, Sweden.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tegefjäll Target entity description: Tegefjäll is a small ski resort settlement in the Åre ski area of Jämtland, Sweden.
-
A.
Helagsfjället
Helagsfjället is a prominent mountain massif in Sweden known for its glacier, popular hiking trails, and rich alpine scenery.
-
B.
Sonfjället
Sonfjället is a prominent mountain and national park in central Sweden, known for its rounded peak, extensive forests, and rich wildlife including one of the country’s oldest bear populations.
-
C.
Ramnefjellet
Ramnefjellet is a mountain in Norway best known for the massive rockslides in the early 20th century that caused catastrophic tsunamis in the nearby lake Lovatnet.
-
D.
Heilefjellet
Heilefjellet is a mountain located in the coastal municipality of Bremanger in Vestland county, western Norway.
-
E.
Råðdjärum
Råðdjärum is the Elfdalian-language name for the Elfdalian Language Council, an organization dedicated to preserving and promoting the Elfdalian language.
- F. None of above. chosen
Provenance (5 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e6338081908aa03ee3dcbe5f70 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003556630081909e60e378e97b06fb |
completed | May 10, 2026, 7:35 a.m. |
| NEDg | Description generation | batch_6a0036e07d2081908db03dcc133f8421 |
completed | May 10, 2026, 7:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00384f51d081909a5ab0630f82d173 |
completed | May 10, 2026, 7:48 a.m. |
Created at: April 10, 2026, 5:07 a.m.