Triple
T8257624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yunnan cuisine |
E193110
|
entity |
| Predicate | hasDish |
P17589
|
FINISHED |
| Object |
er kuai
Er kuai is a traditional Yunnan rice cake made from steamed and pounded glutinous rice, often grilled, stir-fried, or served with various savory toppings.
|
E721203
|
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: er kuai | Statement: [Yunnan cuisine, hasDish, er kuai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: er kuai Context triple: [Yunnan cuisine, hasDish, er kuai]
-
A.
Kuaiji
Kuaiji was an important ancient Chinese city in what is now Shaoxing, Zhejiang, historically known as a political and cultural center in the Yue region.
-
B.
Yikatong
Yikatong is Beijing’s contactless smart card system used for paying fares on public transportation and other city services.
-
C.
Xiaoerjing
Xiaoerjing is an Arabic-based writing system historically used to transcribe Sinitic languages, especially by Muslim communities in China such as the Hui.
-
D.
Kuichong
Kuichong is a town within Shenzhen’s Dapeng New District in Guangdong Province, China, known for its coastal scenery and proximity to popular beaches and nature reserves.
-
E.
Qibao
Qibao is an ancient water town and popular tourist area in Shanghai, known for its historic streets, canals, and traditional architecture.
- 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: er kuai Triple: [Yunnan cuisine, hasDish, er kuai]
Generated description
Er kuai is a traditional Yunnan rice cake made from steamed and pounded glutinous rice, often grilled, stir-fried, or served with various savory toppings.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: er kuai Target entity description: Er kuai is a traditional Yunnan rice cake made from steamed and pounded glutinous rice, often grilled, stir-fried, or served with various savory toppings.
-
A.
Kuaiji
Kuaiji was an important ancient Chinese city in what is now Shaoxing, Zhejiang, historically known as a political and cultural center in the Yue region.
-
B.
Yikatong
Yikatong is Beijing’s contactless smart card system used for paying fares on public transportation and other city services.
-
C.
Xiaoerjing
Xiaoerjing is an Arabic-based writing system historically used to transcribe Sinitic languages, especially by Muslim communities in China such as the Hui.
-
D.
Kuichong
Kuichong is a town within Shenzhen’s Dapeng New District in Guangdong Province, China, known for its coastal scenery and proximity to popular beaches and nature reserves.
-
E.
Qibao
Qibao is an ancient water town and popular tourist area in Shanghai, known for its historic streets, canals, and traditional architecture.
- 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_69ca82dfad9c8190b8cd18fb89f50f40 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb78fce9308190ac36512e80b06b52 |
completed | March 31, 2026, 7:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd355bef508190894bd01ec39e83f6 |
completed | April 1, 2026, 3:10 p.m. |
| NEDg | Description generation | batch_69cd37a7ea30819094b1c140868fab5f |
completed | April 1, 2026, 3:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cd4f0055dc8190803a7c412533aec4 |
completed | April 1, 2026, 4:59 p.m. |
Created at: March 30, 2026, 5:49 p.m.