Triple
T23372014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 松輪島 |
E593499
|
entity |
| Predicate | 地形 |
P9701
|
FINISHED |
| Object | 火山島 |
—
|
LITERAL 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: 火山島 | Statement: [松輪島, 地形, 火山島]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 地形 Context triple: [松輪島, 地形, 火山島]
-
A.
terrainFeature
Indicates a relationship where one entity is a natural or constructed landform or surface characteristic associated with a given location or area.
-
B.
landscapeType
chosen
Indicates the kind or category of natural terrain or scenery that characterizes a place or area.
-
C.
terrainStyle
Indicates the characteristic type or pattern of terrain associated with an entity or location.
-
D.
geographicalNature
Indicates the natural geographic characteristics or physical landscape type associated with a place or region.
-
E.
topographicalCategory
Indicates the type of landform or surface feature that characterizes the physical terrain associated with an entity.
- F. None of above.
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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3af45ec8190a32aa4e5f04f6756 |
completed | April 29, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69f061c7aaa48190a58ce93f87155ffc |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:32 p.m.