Triple
T28837826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hương Sơn scenic area |
E728232
|
entity |
| Predicate | mainTempleComplex |
P166281
|
FINISHED |
| Object | Perfume Pagoda complex |
—
|
NE NERFINISHED |
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: Perfume Pagoda complex | Statement: [Hương Sơn scenic area, mainTempleComplex, Perfume Pagoda complex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainTempleComplex Context triple: [Hương Sơn scenic area, mainTempleComplex, Perfume Pagoda complex]
-
A.
mainTemple
Indicates that one entity serves as the primary or central temple associated with another entity.
-
B.
templeComplexFeature
chosen
Indicates that one entity is a structural or functional feature that forms part of a larger temple complex.
-
C.
templeComplexAreaInAcres
Indicates the total land area of a temple complex measured in acres.
-
D.
elementRepresentedByMainTemple
Indicates that a particular element is symbolized or embodied by the main temple in a given religious or cultural context.
-
E.
mainTempleState
Indicates that a temple serves as the primary or central religious site within a particular state or region.
- 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_69f0319e8e7c8190b37288c8845b9dbc |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 28, 2026, 6:39 a.m.