Triple
T23106570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Huaiyang cuisine |
E576184
|
entity |
| Predicate | famousDish |
P6863
|
FINISHED |
| Object |
Wensi tofu
Wensi tofu is a classic Chinese tofu dish renowned for its extremely fine knife work and delicate, soup-like presentation, often associated with refined Jiangsu cuisine.
|
E1571636
|
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: Wensi tofu | Statement: [Huaiyang cuisine, famousDish, Wensi tofu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wensi tofu Context triple: [Huaiyang cuisine, famousDish, Wensi tofu]
-
A.
mapo tofu
Mapo tofu is a classic Sichuan Chinese dish featuring soft tofu and minced meat in a spicy, numbing chili and Sichuan peppercorn sauce.
-
B.
Mofu-Sud
Mofu-Sud is a Chadic language spoken by the Mofu people in northern Cameroon.
-
C.
Den-en-chōfu
Den-en-chōfu is an upscale residential neighborhood in Tokyo known for its garden-city design, tree-lined streets, and low-rise, affluent housing.
-
D.
Tofol
Tofol is the administrative center and main town of Kosrae State in the Federated States of Micronesia.
-
E.
Maoke Plate
The Maoke Plate is a minor tectonic plate in the region of New Guinea, contributing to the complex and active plate boundary interactions in eastern Indonesia.
- 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: Wensi tofu Triple: [Huaiyang cuisine, famousDish, Wensi tofu]
Generated description
Wensi tofu is a classic Chinese tofu dish renowned for its extremely fine knife work and delicate, soup-like presentation, often associated with refined Jiangsu cuisine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wensi tofu Target entity description: Wensi tofu is a classic Chinese tofu dish renowned for its extremely fine knife work and delicate, soup-like presentation, often associated with refined Jiangsu cuisine.
-
A.
mapo tofu
Mapo tofu is a classic Sichuan Chinese dish featuring soft tofu and minced meat in a spicy, numbing chili and Sichuan peppercorn sauce.
-
B.
Mofu-Sud
Mofu-Sud is a Chadic language spoken by the Mofu people in northern Cameroon.
-
C.
Den-en-chōfu
Den-en-chōfu is an upscale residential neighborhood in Tokyo known for its garden-city design, tree-lined streets, and low-rise, affluent housing.
-
D.
Tofol
Tofol is the administrative center and main town of Kosrae State in the Federated States of Micronesia.
-
E.
Maoke Plate
The Maoke Plate is a minor tectonic plate in the region of New Guinea, contributing to the complex and active plate boundary interactions in eastern Indonesia.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0bb27c8190a17942d9b88bb158 |
completed | April 29, 2026, 4:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c23e606cc8190b0f51e22318250ad |
completed | May 19, 2026, 8:48 a.m. |
| NEDg | Description generation | batch_6a0c28083b548190b8773691b6cc1e39 |
completed | May 19, 2026, 9:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c28f3c9288190b9ee0e5c4911ee9b |
completed | May 19, 2026, 9:10 a.m. |
Created at: April 17, 2026, 3:58 p.m.