Triple
T10109986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 湘语 |
E218213
|
entity |
| Predicate | majorCityWhereSpoken |
P35609
|
FINISHED |
| Object | 益阳市 |
E172641
|
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: 益阳市 | Statement: [湘语, majorCityWhereSpoken, 益阳市]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 益阳市 Context triple: [湘语, majorCityWhereSpoken, 益阳市]
-
A.
浏阳
浏阳是中国湖南省东部的一座县级市，以烟花爆竹产业和红色革命历史而闻名。
-
B.
Yiyang Municipal People's Government
Yiyang Municipal People's Government is the principal administrative authority responsible for local governance, public services, and policy implementation in the prefecture-level city of Yiyang in Hunan Province, China.
-
C.
Yiyang
chosen
Yiyang is a prefecture-level city in south-central China known for its location along the Zi River and its role as an important regional center in Hunan Province.
-
D.
新余市
新余市 is a county-level city in central Jiangxi Province, China, known for its steel industry and rapid industrial development.
-
E.
Loudi
Loudi is a prefecture-level city in south-central China known for its role as an industrial and transportation hub within Hunan Province.
- 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_69ca83da93fc8190b54e44bc2b34857c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd0cdb3c88190a74f75bf865664f3 |
completed | April 2, 2026, 2:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2cc1805d08190bc39aadf1e84a569 |
completed | April 5, 2026, 8:54 p.m. |
Created at: March 30, 2026, 9:03 p.m.