Triple
T17442816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 马鞍山 |
E424699
|
entity |
| Predicate | nearCity |
P350
|
FINISHED |
| Object | 南京市 |
—
|
NE NERFINISHED |
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: 南京市 | Statement: [马鞍山, nearCity, 南京市]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 南京市 Context triple: [马鞍山, nearCity, 南京市]
-
A.
Nanjing
chosen
Nanjing is a major city in eastern China, historically significant as a former national capital and cultural center, and now an important political, economic, and educational hub on the Yangtze River.
-
B.
Xuzhou
Xuzhou is a major historic city in northern Jiangsu Province, China, known as a strategic transportation hub and former battleground in multiple Chinese conflicts.
-
C.
Changzhou
Changzhou is a major industrial and commercial city in Jiangsu Province, eastern China, known for its manufacturing base and location along the Yangtze River.
-
D.
Huaian
Huaian is a historic prefecture-level city in northern Jiangsu Province, China, known as the birthplace of Premier Zhou Enlai and for its Grand Canal heritage.
-
E.
Wuxi
Wuxi is a major industrial and cultural city in eastern China, located near Lake Tai and known for its manufacturing, canals, and historic gardens.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44ff927ec8190995798f569e913ba |
completed | April 19, 2026, 3:46 a.m. |
Created at: April 10, 2026, 5:47 a.m.