Triple
T16021478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Tokachi |
E388606
|
entity |
| Predicate | JapaneseName |
P744
|
FINISHED |
| Object | 十勝岳 |
E1167977
|
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: 十勝岳 | Statement: [Mount Tokachi, JapaneseName, 十勝岳]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 十勝岳 Context triple: [Mount Tokachi, JapaneseName, 十勝岳]
-
A.
十勝岳連峰
chosen
十勝岳連峰 is a volcanic mountain range in central Hokkaido, Japan, known for its active volcanoes, alpine scenery, and popular hiking routes.
-
B.
槍ヶ岳
槍ヶ岳 is a sharply pointed, spear-shaped peak in Japan’s Hida Mountains, renowned as one of the most iconic and challenging summits in the Northern Alps.
-
C.
Mount Kusatsu-Shirane
Mount Kusatsu-Shirane is an active stratovolcano in central Honshu, Japan, known for its acidic crater lakes and popular nearby hot spring resort of Kusatsu Onsen.
-
D.
羅臼岳
羅臼岳 is a prominent active stratovolcano and one of the major peaks of Japan’s Shiretoko Peninsula in eastern Hokkaido, known for its rugged alpine scenery and wildlife-rich national park setting.
-
E.
Eboshidake
Eboshidake is a mountain in Japan, known as one of the peaks in the volcanic landscape of the Kirishima mountain range on Kyushu.
- 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e183231f2c81908f4e4037c3aa180b |
completed | April 17, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf2c6128819091d8f3710578834e |
completed | May 10, 2026, 12:19 a.m. |
Created at: April 10, 2026, 4:55 a.m.