Triple
T12028913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgian Jerusalem lectionary |
E286351
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Georgian-language manuscript |
C5613
|
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: Georgian-language manuscript Context triple: [Georgian Jerusalem lectionary, instanceOf, Georgian-language manuscript]
-
A.
Georgian-language book
chosen
A Georgian-language book is a written work whose primary text is composed in the Georgian language, typically using the Georgian script and reflecting Georgian linguistic and cultural context.
-
B.
Glagolitic manuscript
A Glagolitic manuscript is a handwritten document produced using the Glagolitic alphabet, one of the earliest Slavic scripts, typically preserving religious, liturgical, or legal texts from the medieval Slavic cultural sphere.
-
C.
Kartvelian language
A Kartvelian language is a member of a small family of indigenous languages of the South Caucasus, including Georgian, Svan, Mingrelian, and Laz, characterized by complex phonology and morphology and no proven genetic relation to other language families.
-
D.
Georgian inscription
A Georgian inscription is a text carved, written, or otherwise rendered in the Georgian script, typically found on monuments, buildings, artifacts, or manuscripts, conveying historical, religious, or commemorative information.
-
E.
regional variety of the Georgian language
A regional variety of the Georgian language is a geographically or socially localized form of Georgian characterized by distinct phonological, lexical, and sometimes grammatical features while remaining mutually intelligible with the standard language.
- 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_69d6ab4669e48190b59246358b0383ab |
completed | April 8, 2026, 7:23 p.m. |
Created at: April 8, 2026, 9:47 p.m.