Triple
T8906475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 外滩 |
E212071
|
entity |
| Predicate | 景观元素 |
P45658
|
FINISHED |
| Object | 历史建筑立面灯光 |
—
|
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: 历史建筑立面灯光 | Statement: [外滩, 景观元素, 历史建筑立面灯光]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 景观元素 Context triple: [外滩, 景观元素, 历史建筑立面灯光]
-
A.
landscapeElement
chosen
Indicates that one entity functions as a landscape-related feature or component in relation to another entity.
-
B.
landscapeType
Indicates the kind or category of natural terrain or scenery that characterizes a place or area.
-
C.
立地特性
Indicates the characteristics or qualities of a location that define its situational conditions or advantages in relation to its surroundings.
-
D.
landscapeAbstraction
Indicates that one entity is an abstract or non-literal representation derived from the landscape or its features.
-
E.
landscapeConcept
Indicates a conceptual or thematic relationship involving landscapes, such as ideas, interpretations, or abstract representations of landscape.
- 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_69ca839255248190b43984294abd92ae |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc64c51d6c819098dc33a480dfd462 |
completed | April 1, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69cc5ecf55248190a29f00fbf99f13c4 |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:55 p.m.