Triple
T4060393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 颐和园 |
E86196
|
entity |
| Predicate | 规划格局 |
P48747
|
FINISHED |
| Object | 以万寿山为主景 |
—
|
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: 以万寿山为主景 | Statement: [颐和园, 规划格局, 以万寿山为主景]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 规划格局 Context triple: [颐和园, 规划格局, 以万寿山为主景]
-
A.
urbanPlanningFunction
Indicates a functional role or purpose that something serves within the planning, organization, or management of urban spaces and infrastructure.
-
B.
urbanPlanningStyle
Indicates the characteristic approach or methodology used in planning and organizing urban spaces and development.
-
C.
architecturalPlanner
Indicates a relationship where an entity is responsible for designing, organizing, or planning the architectural structure or layout of another entity.
-
D.
urbanDesignType
Indicates the specific category or style of urban design that characterizes or is applied to a place or project.
-
E.
urbanLayout
chosen
Indicates how the spatial arrangement, organization, and structure of buildings, streets, and public spaces relate to one another within an urban area.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.