Triple
T11741791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 桂川 |
E279172
|
entity |
| Predicate | 関連観光地 |
P47506
|
FINISHED |
| Object | 嵐山公園 |
—
|
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: 嵐山公園 | Statement: [桂川, 関連観光地, 嵐山公園]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連観光地 Context triple: [桂川, 関連観光地, 嵐山公園]
-
A.
relatedAttraction
chosen
Indicates that one attraction is associated with or connected to another attraction in some relevant way.
-
B.
関連施設
Indicates a relationship where one facility is associated with, connected to, or otherwise related to another facility.
-
C.
hasTouristAttractionRole
Indicates that an entity serves in the capacity or function of a tourist attraction for another entity (such as a place, organization, or area).
-
D.
hasTourismResource
Indicates that a place, area, or entity possesses or is associated with a tourism-related resource, attraction, or facility.
-
E.
connectsToTouristRegion
Indicates that one entity has a direct linkage or association to a tourist region, such as through location, access, or service provision.
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4f191388190bd6ef7e80c41ca48 |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a813cc48190a3dfdc60e8af80ae |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.