Triple
T6791836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghainese |
E155949
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Wu Chinese dialect |
C7052
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Wu Chinese dialect Context triple: [Shanghainese, instanceOf, Wu Chinese dialect]
-
A.
Sinitic language
A Sinitic language is any member of the Chinese branch of the Sino-Tibetan language family, characterized by tonal phonology, analytic grammar, and a shared historical connection to Classical Chinese.
-
B.
Formosan language
A Formosan language is any of the indigenous Austronesian languages spoken by the native peoples of Taiwan, distinct from but historically related to other Austronesian languages.
-
C.
variety of Mandarin Chinese
A variety of Mandarin Chinese is a regional or social form of the Mandarin language distinguished by its phonological, lexical, and sometimes grammatical features while remaining mutually intelligible with other Mandarin forms.
-
D.
Quechuan language
A Quechuan language is any member of a family of indigenous languages of the Andes, primarily spoken in Peru, Bolivia, Ecuador, Colombia, and Argentina, that share common grammatical structures and vocabulary derived from a Proto-Quechuan ancestor.
-
E.
Chinese language variety
chosen
A Chinese language variety is a distinct, historically rooted form of the Chinese language—such as Mandarin, Cantonese, or Shanghainese—characterized by its own phonology, vocabulary, and grammar, and often mutually unintelligible with other such forms.
- F. None of above.
Provenance (1 batch)
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_69c6881770fc8190972b2906390380f5 |
completed | March 27, 2026, 1:37 p.m. |
Created at: March 27, 2026, 2:15 p.m.