Triple
T28741287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swedish Romani |
E731247
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Para-Romani language |
C23958
|
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: Para-Romani language Context triple: [Swedish Romani, instanceOf, Para-Romani language]
-
A.
para-Romani variety
chosen
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.
-
B.
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.
-
C.
Sarmatian language
The Sarmatian language was an extinct Eastern Iranian language (or group of dialects) once spoken by the Sarmatian tribes of the Eurasian steppe, known primarily through onomastic and limited historical evidence.
-
D.
Zaza–Gorani language
The Zaza–Gorani language is a proposed grouping of two closely related Northwestern Iranian languages, Zaza and Gorani, spoken primarily by ethnic Kurdish and related communities in eastern Turkey, northern Iraq, and western Iran.
-
E.
Lezgic language
A Lezgic language is a member of a subgroup of the Northeast Caucasian language family, spoken primarily in southern Dagestan (Russia) and northern Azerbaijan, characterized by complex consonant systems and rich case morphology.
- 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_69f043ecb5c081909ec9da1172d68ece |
completed | April 28, 2026, 5:21 a.m. |
Created at: April 28, 2026, 6:03 a.m.