Triple
T16468914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Meakan |
E400007
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Meakan-dake |
—
|
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: Meakan-dake | Statement: [Mount Meakan, romanization, Meakan-dake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Meakan-dake Context triple: [Mount Meakan, romanization, Meakan-dake]
-
A.
Meakan-dake
chosen
Meakan-dake is an active stratovolcano in eastern Hokkaido, Japan, known for its fumarolic activity and scenic alpine landscapes within Akan-Mashu National Park.
-
B.
Oakan-dake
Oakan-dake is a stratovolcano in Hokkaido, Japan, known for its steep, conical shape and location within the Akan volcanic region.
-
C.
Myoken-dake
Myoken-dake is one of the main volcanic peaks of the Unzen volcanic complex on Japan’s Shimabara Peninsula.
-
D.
Minamidake
Minamidake is one of the principal active summit craters of the Sakurajima volcano in Kagoshima Prefecture, Japan.
-
E.
Nyoigatake
Nyoigatake is a mountain in Kyoto, Japan, best known for the giant "大" character bonfire lit on its slope during the annual Gozan no Okuribi festival.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32dce342081909cad56dc92de13a2 |
completed | April 18, 2026, 7:07 a.m. |
Created at: April 10, 2026, 5:11 a.m.