Triple
T30155517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 黄鹤楼 |
E766508
|
entity |
| Predicate | 所属文化类型 |
P81632
|
FINISHED |
| Object | 古典园林与楼阁文化 |
—
|
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: 古典园林与楼阁文化 | Statement: [黄鹤楼, 所属文化类型, 古典园林与楼阁文化]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属文化类型 Context triple: [黄鹤楼, 所属文化类型, 古典园林与楼阁文化]
-
A.
culturalType
chosen
Indicates the classification of something according to its cultural category, style, or tradition.
-
B.
culturalCategory
Indicates that one entity classifies or groups another entity according to a particular culture, tradition, or culturally defined type.
-
C.
culturalIdentifier
Indicates that one entity serves as a marker, label, or attribute that identifies or characterizes the cultural affiliation, background, or context of another entity.
-
D.
groupCulture
Indicates that a group shares common norms, values, practices, or traditions that characterize its collective way of life.
-
E.
culturalPrototypeFor
Indicates that one entity serves as a culturally recognized model or standard example for understanding or interpreting another entity.
- 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_69f22479cd088190ab4c6f3fce39d1c5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67ed72fb08190955d6bfd90dd3b8e |
completed | May 2, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:20 p.m.