Triple
T36095173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 狮子林 |
E1044039
|
entity |
| Predicate | 假山特色 |
P50854
|
FINISHED |
| Object | 以太湖石堆叠成大规模假山群 |
—
|
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: 以太湖石堆叠成大规模假山群 | Statement: [狮子林, 假山特色, 以太湖石堆叠成大规模假山群]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 假山特色 Context triple: [狮子林, 假山特色, 以太湖石堆叠成大规模假山群]
-
A.
ornamentalFeature
chosen
Indicates that one entity serves as a decorative or embellishing feature of another entity.
-
B.
hasLandscapeArchitecturalStyle
Indicates that something (such as a site or landscape) is designed or characterized according to a particular landscape architectural style.
-
C.
featuresSculptureOf
Indicates that one entity includes or displays a sculpture that depicts or represents another entity.
-
D.
artisticSeriesFeature
Indicates that one entity is included as a featured component or installment within an artistic series created or presented by another entity.
-
E.
hasHillFigure
Indicates that a location or area contains or features a hill figure (a large design or image created on a hillside).
- 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_69f76e32d60c8190ba781ffaaab4aa3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.