Triple
T28500722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pumi |
E721221
|
entity |
| Predicate | associatedMountainEnvironment |
P945
|
FINISHED |
| Object | Hengduan Mountains |
—
|
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: Hengduan Mountains | Statement: [Pumi, associatedMountainEnvironment, Hengduan Mountains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedMountainEnvironment Context triple: [Pumi, associatedMountainEnvironment, Hengduan Mountains]
-
A.
mountainType
Indicates the specific classification or category of a mountain based on its geological or physical characteristics.
-
B.
borderMountainOf
Indicates that a mountain lies along or forms part of the border of a specified region or entity.
-
C.
mountainFeature
Indicates that one entity is a notable physical or geographical feature associated with, located on, or forming part of a mountain.
-
D.
mountainAccess
Indicates that an entity has the ability, right, or means to reach, enter, or utilize a mountain or mountainous area.
-
E.
mountainSystem
chosen
Indicates a relationship where multiple mountains are grouped together as part of the same connected or coherent mountain system or range.
- 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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a016ebba0448190b5319243e1b2feca |
completed | May 11, 2026, 5:52 a.m. |
| PD | Predicate disambiguation | batch_6a016d2486b4819085efe197ee21b707 |
completed | May 11, 2026, 5:46 a.m. |
Created at: April 28, 2026, 3:06 a.m.