Triple
T15729295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akan Onsen |
E381298
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mount Meakan |
—
|
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: Mount Meakan | Statement: [Akan Onsen, near, Mount Meakan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Meakan Context triple: [Akan Onsen, near, Mount Meakan]
-
A.
Mount Meakan
chosen
Mount Meakan is an active stratovolcano on Japan’s Hokkaido island, known for its rugged landscape, volcanic craters, and popular hiking trails.
-
B.
Mount Maetokachi
Mount Maetokachi is a volcanic peak in Japan that forms part of the Tokachi Volcanic Group on the island of Hokkaido.
-
C.
Mount Akutan
Mount Akutan is an active stratovolcano in Alaska’s Aleutian Islands, known for frequent eruptions and geothermal activity.
-
D.
Mount Eniwa
Mount Eniwa is an active stratovolcano on Japan’s northern island of Hokkaido, known for its scenic hiking trails and proximity to Lake Shikotsu within Shikotsu-Toya National Park.
-
E.
Mount Erice
Mount Erice is a prominent mountain in western Sicily, Italy, known for its medieval hilltop town of Erice and panoramic views over the surrounding coast and islands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb4cc0081909efe330339474017 |
completed | April 16, 2026, 2:55 a.m. |
Created at: April 10, 2026, 4:46 a.m.