Triple
T24931800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junshan Island |
E619005
|
entity |
| Predicate | primaryTouristActivities |
P1769
|
FINISHED |
| Object | sightseeing |
—
|
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: sightseeing | Statement: [Junshan Island, primaryTouristActivities, sightseeing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryTouristActivities Context triple: [Junshan Island, primaryTouristActivities, sightseeing]
-
A.
primaryTourismHub
Indicates that a location serves as the main center or focal point for tourism activities within a given area or region.
-
B.
touringActivity
Indicates an activity where an entity travels from place to place, typically for visiting, performing, or sightseeing purposes.
-
C.
tourismType
chosen
Indicates the specific category or kind of tourism activity or experience associated with an entity.
-
D.
countryTourismCategory
Indicates the tourism classification or category assigned to a country based on its tourism characteristics or status.
-
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_69e2fab9edd88190b86004a78a28bc20 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f6978fe97081908fe568091ad9b159 |
completed | May 3, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69f69661e6ec8190948251c7516a32ad |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 18, 2026, 5:30 a.m.