Triple
T13851129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shuozhou |
E332942
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Datong |
E331697
|
NE 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: Datong | Statement: [Shuozhou, borderedBy, Datong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Datong Context triple: [Shuozhou, borderedBy, Datong]
-
A.
Datong
chosen
Datong is a historic industrial city in northern China known for its coal production and nearby cultural landmarks such as the Yungang Grottoes.
-
B.
Xinzhou
Xinzhou is a prefecture-level city in northern China known for its historical sites and location within Shanxi Province’s coal-rich and culturally significant region.
-
C.
Fenyang
Fenyang is a county-level city in Shanxi Province, China, known for its historical heritage and role in regional commerce and culture.
-
D.
Taiyuan
Taiyuan is the capital and largest city of Shanxi Province in northern China, known as an important industrial and transportation hub with a long imperial history.
-
E.
Taiyuan
Taiyuan was a historical Chinese era name used during the reign of the Eastern Jin emperor Sun Liang.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02d8fb788190baef7537be2baecb |
completed | April 14, 2026, 9:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3cfd550c81909ad487d3d7d7c313 |
completed | May 8, 2026, 1:31 a.m. |
Created at: April 9, 2026, 10:14 p.m.