Triple
T16404854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beppu–Shimabara graben |
E398399
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Unzen volcano |
E785271
|
NE FINISHED |
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: Unzen volcano | Statement: [Beppu–Shimabara graben, hasPart, Unzen volcano]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Unzen volcano Context triple: [Beppu–Shimabara graben, hasPart, Unzen volcano]
-
A.
Mount Unzen
chosen
Mount Unzen is an active volcanic complex on Japan’s Kyushu Island known for its destructive eruptions and associated pyroclastic flows.
-
B.
Ashitaka volcano
Ashitaka volcano is a stratovolcano in central Japan located near Mount Fuji, forming part of the broader volcanic landscape of the region.
-
C.
Hakone volcano
Hakone volcano is an active complex volcano in Japan known for its caldera, hot springs, and role in the geologically dynamic region near Mount Fuji.
-
D.
Beppu
Beppu is a famous Japanese city on the island of Kyushu renowned for its numerous hot springs and geothermal attractions.
-
E.
Ushishir Volcano
Ushishir Volcano is an active volcanic complex forming part of a partially submerged caldera in the central Kuril Islands of Russia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e327d1f16481909adb19dab86dcc72 |
completed | April 18, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a50665d081908c07fe3cb59088b3 |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:09 a.m.