Triple
T16584107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suzhounese |
E402908
|
entity |
| Predicate | subgroupOf |
P10
|
FINISHED |
| Object | Taihu Wu |
E404458
|
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: Taihu Wu | Statement: [Suzhounese, subgroupOf, Taihu Wu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taihu Wu Context triple: [Suzhounese, subgroupOf, Taihu Wu]
-
A.
Taihu Wu
chosen
Taihu Wu is a major subgroup of the Wu varieties of Chinese, spoken in and around the Yangtze River Delta including cities such as Shanghai, Suzhou, and Hangzhou.
-
B.
Pai Mei
Pai Mei is a legendary, ruthless martial arts master in Quentin Tarantino’s Kill Bill saga, known for his brutal training methods and near-mythic fighting skills.
-
C.
Wu Ta-You
Wu Ta-You was a prominent Chinese theoretical physicist often regarded as the father of modern Chinese physics.
-
D.
Wu
Wu is a common Chinese surname borne by many notable individuals across politics, academia, entertainment, and sports.
-
E.
Oujiang Wu
Oujiang Wu is a subgroup of the Wu branch of Chinese, spoken primarily in and around Wenzhou in China’s Zhejiang province and known for its distinct phonology and relative unintelligibility to speakers of other Chinese varieties.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35999f80c8190852fd4137bc45a80 |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ef2d6048190954144ab848760ec |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:16 a.m.