Triple
T8646895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Propontis Tsakonian |
E204998
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Tsakonian dialect |
C2083
|
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: Tsakonian dialect Context triple: [Propontis Tsakonian, instanceOf, Tsakonian dialect]
-
A.
Hellenic language
The Hellenic language is a branch of the Indo-European language family encompassing Ancient, Medieval, and Modern Greek and their dialects, which have evolved over millennia in the Hellenic world.
-
B.
Byzantine Greek
Byzantine Greek is the form of the Greek language used in the Eastern Roman (Byzantine) Empire from late antiquity to the fall of Constantinople, characterized by a mixture of classical, Koine, and emerging medieval features in grammar, vocabulary, and style.
-
C.
Vlach language
The Vlach language is a Romance language or group of dialects spoken by Vlach communities in the Balkans, characterized by strong influence from surrounding Slavic, Greek, and Albanian languages.
-
D.
Greek language variety
chosen
A Greek language variety is a distinct form of the Greek language, characterized by specific phonological, grammatical, lexical, and pragmatic features associated with particular regions, communities, or social groups.
-
E.
para-Romani variety
A para-Romani variety is a mixed language in which Romani-derived vocabulary is embedded into the grammatical structure of a surrounding majority language, typically used as an in-group code by Romani or Romani-associated communities.
- 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_69ca834e56848190abb0eeaec9dedd32 |
completed | March 30, 2026, 2:06 p.m. |
Created at: March 30, 2026, 6:28 p.m.