Triple
T31664954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyongyang speech |
E808100
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Korean language variety |
C19701
|
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: Korean language variety Context triple: [Pyongyang speech, instanceOf, Korean language variety]
-
A.
language of South Korea
chosen
The language of South Korea is Korean, a Koreanic language written primarily in the Hangul script and used in government, education, media, and daily communication throughout the country.
-
B.
Chinese language variety
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.
-
C.
variety of the Sehwi language
A variety of the Sehwi language is a regional or social form of Sehwi characterized by distinct phonological, lexical, or grammatical features within the broader Sehwi-speaking community.
-
D.
Indigenous language variety
An Indigenous language variety is a distinct form or dialect of a language traditionally spoken by an Indigenous community, reflecting its unique cultural, historical, and social practices.
-
E.
Kayan language variety
A Kayan language variety is a specific linguistic form or dialect within the Kayan language family, spoken by Kayan communities and characterized by its own phonological, lexical, and grammatical features.
- 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_69f348dbeef4819080b446a7feb6340b |
completed | April 30, 2026, 12:19 p.m. |
Created at: April 30, 2026, 10:59 p.m.