Triple
T33836986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 安定门 |
E867258
|
entity |
| Predicate | 遗存形式 |
P57740
|
FINISHED |
| Object | 以地名、道路、桥梁等形式保留 |
—
|
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: 以地名、道路、桥梁等形式保留 | Statement: [安定门, 遗存形式, 以地名、道路、桥梁等形式保留]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 遗存形式 Context triple: [安定门, 遗存形式, 以地名、道路、桥梁等形式保留]
-
A.
retainsHeritageOf
Indicates that one entity preserves, maintains, or keeps alive the cultural, historical, or traditional legacy originating from another entity.
-
B.
culturalRemains
Indicates that one entity consists of or contains physical or material traces left by a culture, such as artifacts, structures, or other archaeological evidence.
-
C.
heritageType
Indicates the classification of an entity’s cultural or natural heritage category or type within a heritage framework.
-
D.
styleOfReconstruction
Indicates the specific method or approach used to reconstruct or restore something from its original or prior state.
-
E.
remnantType
chosen
Indicates the specific kind or category of remnant that results from or is associated with an entity or process.
- 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_69f34992ad40819087760ed939bd2a7a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7002f38308190af948b97a35a5b09 |
completed | May 3, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.