Triple
T17451766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 上毛三山 |
E424928
|
entity |
| Predicate | isCollectiveNameFor |
P52939
|
FINISHED |
| Object | 榛名山 |
—
|
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: 榛名山 | Statement: [上毛三山, isCollectiveNameFor, 榛名山]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 榛名山 Context triple: [上毛三山, isCollectiveNameFor, 榛名山]
-
A.
榛名山
chosen
榛名山 is an active volcanic mountain and popular scenic and spiritual destination in Gunma Prefecture, Japan, known for its caldera lake, hot springs, and historic shrines.
-
B.
稲荷山
稲荷山 is a sacred mountain in Kyoto, Japan, best known as the site of Fushimi Inari Taisha and its thousands of vermilion torii gates.
-
C.
比叡山
比叡山は滋賀県と京都府にまたがる山で、日本仏教に大きな影響を与えた天台宗の総本山・延暦寺が置かれている霊峰です。
-
D.
野呂山
野呂山 is a scenic mountain in Hiroshima Prefecture, Japan, known for its panoramic views of the Seto Inland Sea and popular hiking and sightseeing spots.
-
E.
秩父山地
秩父山地 is a mountainous region in central Japan spanning parts of Saitama, Yamanashi, Nagano, and Tokyo, known for its rugged peaks, rich forests, and popular hiking areas.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4513e57248190824b540865311f44 |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.