Triple
T10002116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meixian Hakka |
E197351
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object |
Meixian tuhua
Meixian tuhua is a local Chinese dialect spoken in the Meixian region of Guangdong, closely associated with but distinct from standard Hakka.
|
E833752
|
NE FINISHED |
How this triple was built (4 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: Meixian tuhua | Statement: [Meixian Hakka, alternativeName, Meixian tuhua]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Meixian tuhua Context triple: [Meixian Hakka, alternativeName, Meixian tuhua]
-
A.
Xuanhu
Xuanhu is the art name of Xu Guangqi, a prominent late Ming dynasty scholar-official, scientist, and collaborator of Matteo Ricci in introducing Western science to China.
-
B.
Meidi Dadao
Meidi Dadao is a metro station in Guangzhou, China, serving as a terminus on Guangzhou Metro Line 7.
-
C.
Xiaomeisha
Xiaomeisha is a popular coastal resort area in Shenzhen, China, known for its sandy beaches, seaside recreation, and tourist attractions.
-
D.
Zhujiajiao
Zhujiajiao is an ancient water town on the outskirts of Shanghai, famed for its historic canals, stone bridges, and traditional architecture.
-
E.
Majiabao
Majiabao is a neighborhood-level area located within Beijing’s Fengtai District, known primarily as a residential and commercial urban locality.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Meixian tuhua Triple: [Meixian Hakka, alternativeName, Meixian tuhua]
Generated description
Meixian tuhua is a local Chinese dialect spoken in the Meixian region of Guangdong, closely associated with but distinct from standard Hakka.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Meixian tuhua Target entity description: Meixian tuhua is a local Chinese dialect spoken in the Meixian region of Guangdong, closely associated with but distinct from standard Hakka.
-
A.
Xuanhu
Xuanhu is the art name of Xu Guangqi, a prominent late Ming dynasty scholar-official, scientist, and collaborator of Matteo Ricci in introducing Western science to China.
-
B.
Meidi Dadao
Meidi Dadao is a metro station in Guangzhou, China, serving as a terminus on Guangzhou Metro Line 7.
-
C.
Xiaomeisha
Xiaomeisha is a popular coastal resort area in Shenzhen, China, known for its sandy beaches, seaside recreation, and tourist attractions.
-
D.
Zhujiajiao
Zhujiajiao is an ancient water town on the outskirts of Shanghai, famed for its historic canals, stone bridges, and traditional architecture.
-
E.
Majiabao
Majiabao is a neighborhood-level area located within Beijing’s Fengtai District, known primarily as a residential and commercial urban locality.
- F. None of above. chosen
Provenance (5 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc9078788190a4e75dd7ff830c63 |
completed | April 2, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d25857f0988190aebe8951f7c0ef86 |
completed | April 5, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_69d2594b5e5081908f7cc4af4d10b4a8 |
completed | April 5, 2026, 12:44 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d25a31c158819096163ba8107523f1 |
completed | April 5, 2026, 12:48 p.m. |
Created at: March 30, 2026, 8:51 p.m.