Triple
T17630759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pingcheng |
E429969
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | present-day Datong |
—
|
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: present-day Datong | Statement: [Pingcheng, locatedIn, present-day Datong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: present-day Datong Context triple: [Pingcheng, locatedIn, present-day 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.
Datong Gan
Datong Gan is a regional variety of the Gan branch of Chinese, spoken primarily in and around Datong in Jiangxi Province.
-
C.
Datong shu
Datong shu is a utopian political and philosophical treatise by Chinese reformer Kang Youwei that envisions a future world of universal equality and social harmony.
-
D.
Shangdu
Shangdu was the summer capital of Kublai Khan’s Yuan dynasty in China, later immortalized in Western literature as the fabled city of Xanadu.
-
E.
Fenyang, Shanxi
Fenyang, Shanxi is a county-level city in central Shanxi Province, China, known for its historical heritage and as the hometown of acclaimed film director Jia Zhangke.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dc01b1c819099e3329cfb8cb77f |
completed | April 19, 2026, 5:53 a.m. |
Created at: April 10, 2026, 5:52 a.m.