Triple
T34220188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Mari |
E877902
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Uralic proto-language |
C58739
|
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: Uralic proto-language Context triple: [Proto-Mari, instanceOf, Uralic proto-language]
-
A.
Uralic language
A Uralic language is a member of the Uralic language family, originating in Northern Eurasia and characterized by features such as agglutinative morphology, extensive case systems, and vowel harmony, including languages like Finnish, Hungarian, and Estonian.
-
B.
Finnic language
A Finnic language is a member of the Uralic language family spoken primarily around the Baltic Sea region, including languages such as Finnish, Estonian, and Karelian, characterized by agglutinative morphology and vowel harmony.
-
C.
Paleo-European language
A Paleo-European language is a hypothesized pre-Indo-European language or group of languages once spoken in prehistoric Europe, known primarily through substratum influences, place names, and limited archaeological and linguistic reconstruction.
-
D.
Northeast Caucasian language
A Northeast Caucasian language is a member of a diverse family of languages spoken primarily in the northeastern Caucasus region, characterized by complex consonant systems and rich case morphology.
-
E.
Baltic language
A Baltic language is a member of the Indo-European language family spoken primarily around the eastern coast of the Baltic Sea, characterized by conservative grammatical features and rich inflectional morphology.
- F. None of above. chosen
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_69f349b0b4bc819088c1552424089ee9 |
completed | April 30, 2026, 12:23 p.m. |
Created at: May 1, 2026, 1:55 a.m.