Triple
T1854905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mkhedruli |
E41679
|
entity |
| Predicate | usedForWriting |
P8571
|
FINISHED |
| Object | Georgian language |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
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.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Georgian language | Statement: [Mkhedruli, usedForWriting, Georgian language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedForWriting Context triple: [Mkhedruli, usedForWriting, Georgian language]
-
A.
usedToWrite
chosen
Indicates that one entity served as a tool, medium, or instrument that another entity employed to perform the act of writing.
-
B.
usedFor
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
C.
hasWrittenFor
Indicates that one entity has created written content (such as articles, stories, or texts) for or on behalf of another entity, typically a publication, organization, or platform.
-
D.
likelyWrittenFrom
Indicates that something (such as a text, statement, or perspective) is probably authored or expressed from the viewpoint, context, or position of a particular entity.
-
E.
openedForUseAs
Indicates that something was made available and began functioning in the capacity or role specified by another entity or purpose.
- F. None of above.
Provenance (3 batches)
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_69a8864a83848190a4ec02721306c511 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb231de14819091da3a20ed03c430 |
completed | March 7, 2026, 5:05 a.m. |
| PD | Predicate disambiguation | batch_69abafde4598819099d8229128348fd3 |
completed | March 7, 2026, 4:55 a.m. |
Created at: March 4, 2026, 7:33 p.m.