Triple
T25096130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 熊本市 |
E628592
|
entity |
| Predicate | 観光資源の特徴 |
P84159
|
FINISHED |
| Object | 武家文化と城下町の景観が残る |
—
|
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: 武家文化と城下町の景観が残る | Statement: [熊本市, 観光資源の特徴, 武家文化と城下町の景観が残る]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 観光資源の特徴 Context triple: [熊本市, 観光資源の特徴, 武家文化と城下町の景観が残る]
-
A.
tourismCharacteristic
chosen
Indicates that something has a specific feature, quality, or attribute relevant to tourism, such as what makes a place, service, or activity notable or suitable for tourists.
-
B.
tourismFeature
Indicates that something serves as an attraction, amenity, or point of interest relevant to tourism or visitors.
-
C.
travelCharacteristic
Indicates a quality, feature, or attribute that characterizes how travel or movement is conducted or experienced.
-
D.
hasTourismResource
Indicates that a place, area, or entity possesses or is associated with a tourism-related resource, attraction, or facility.
-
E.
tourismTheme
Indicates the main subject or focus of a tourism-related activity, service, or destination (such as cultural, adventure, or eco-tourism).
- 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_69e2ff2f58e881908340527bc5d34f07 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f464b9651481908d4d7584717f5c59 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:25 a.m.