Triple
T17823031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Kusatsu-Shirane |
E445036
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Kusatsu town |
—
|
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: Kusatsu town | Statement: [Mount Kusatsu-Shirane, near, Kusatsu town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kusatsu town Context triple: [Mount Kusatsu-Shirane, near, Kusatsu town]
-
A.
Kusatsu
Kusatsu is a Japanese city in Shiga Prefecture known as a regional commercial hub and transportation crossroads near Lake Biwa.
-
B.
Teshikaga town
Teshikaga town is a municipality in eastern Hokkaido, Japan, known for its volcanic landscapes, hot spring resorts, and scenic lakes such as Lake Mashu and Lake Kussharo.
-
C.
Kusatsu, Gunma
chosen
Kusatsu, Gunma is a renowned hot spring resort town in Gunma Prefecture, Japan, famous for its high-volume, highly acidic thermal waters and traditional onsen culture.
-
D.
Kusatsu, Shiga
Kusatsu, Shiga is a city in Japan’s Kansai region known as a residential and commercial hub within the greater Kyoto–Osaka metropolitan area.
-
E.
Marugame
Marugame is a coastal city in Japan’s Kagawa Prefecture, known for Marugame Castle and its traditional uchiwa (paper fans) craftsmanship.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4891282a081908d384d45bf444baf |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 10, 2026, 10:15 a.m.