Triple
T28879118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 伊良部大橋 |
E732362
|
entity |
| Predicate | 観光上の利用形態 |
P112497
|
FINISHED |
| Object | レンタカーや自家用車でのドライブスポット |
—
|
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: レンタカーや自家用車でのドライブスポット | Statement: [伊良部大橋, 観光上の利用形態, レンタカーや自家用車でのドライブスポット]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 観光上の利用形態 Context triple: [伊良部大橋, 観光上の利用形態, レンタカーや自家用車でのドライブスポット]
-
A.
tourismType
Indicates the specific category or kind of tourism activity or experience associated with an entity.
-
B.
hasTourismFunction
Indicates that an entity serves a role or purpose related to tourism, such as attracting, accommodating, or providing services to tourists.
-
C.
hasTourismForm
chosen
Indicates that an entity is associated with a particular type or form of tourism activity or service.
-
D.
hasTourismStyle
Indicates the type or style of tourism associated with or characteristic of a particular entity.
-
E.
tourismFeature
Indicates that something serves as an attraction, amenity, or point of interest relevant to tourism or visitors.
- 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_69f05b06807c81909b4bbd4c20403a2b |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65a4d874c819094de2d585e1f5816 |
completed | May 2, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 7:41 a.m.