Triple
T16583777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celestial Capital Peak |
E402900
|
entity |
| Predicate | scenicRank |
P106817
|
FINISHED |
| Object | one of the most famous peaks of Huangshan |
—
|
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: one of the most famous peaks of Huangshan | Statement: [Celestial Capital Peak, scenicRank, one of the most famous peaks of Huangshan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scenicRank Context triple: [Celestial Capital Peak, scenicRank, one of the most famous peaks of Huangshan]
-
A.
numberOfScenicSpots
Indicates the quantity of scenic spots associated with a given entity.
-
B.
hasScenicValue
Indicates that something possesses notable aesthetic or visual appeal, often due to its natural beauty or pleasing surroundings.
-
C.
isPartOfScenicVista
Indicates that something is included within, or contributes to, a larger scenic vista or panoramic view.
-
D.
scenicDescription
chosen
Indicates a descriptive portrayal of the visual or aesthetic qualities of a scene or landscape.
-
E.
hasScenicViewpoints
Indicates that something includes or provides locations specifically intended for enjoying scenic or panoramic views.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35999f80c8190852fd4137bc45a80 |
completed | April 18, 2026, 10:14 a.m. |
| PD | Predicate disambiguation | batch_69e296a7d9d0819088555bca6c936e79 |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:16 a.m.