Triple
T21943397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chang'an dialect |
E541876
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | variety of Middle Chinese |
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: variety of Middle Chinese Context triple: [Chang'an dialect, instanceOf, variety of Middle Chinese]
-
A.
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.
-
B.
variety of Cantonese
A variety of Cantonese is a specific regional or social form of the Cantonese language characterized by distinct phonological, lexical, and sometimes grammatical features.
-
C.
variety of Shina language
A variety of the Shina language is a regional or social dialect of Shina distinguished by its unique phonological, lexical, or grammatical features while remaining mutually intelligible to varying degrees with other Shina dialects.
-
D.
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.
-
E.
variety of Hokkien
A variety of Hokkien is a regional or social dialect of the Hokkien Chinese language distinguished by its unique phonological, lexical, and syntactic features shaped by local history and contact with other languages.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
Created at: April 16, 2026, 7:56 p.m.