Triple
T21657625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levan of Kakheti |
E534507
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Levan |
—
|
NE NERFINISHED |
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: Levan | Statement: [Levan of Kakheti, givenName, Levan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Levan Context triple: [Levan of Kakheti, givenName, Levan]
-
A.
Levan
chosen
Levan is a masculine given name commonly used in Georgia and other parts of the Caucasus region.
-
B.
Tavaeli
Tavaeli is a regional dialect of the Kaili language spoken by communities in Central Sulawesi, Indonesia.
-
C.
Gurieli
Gurieli was a hereditary princely title held by a noble family that ruled the region of Guria in western Georgia.
-
D.
Ivane
Ivane is a Georgian given name most notably borne by historian Ivane Javakhishvili, a key figure in the study of Georgia’s history and culture.
-
E.
Avtandil
Avtandil is the noble and valiant Georgian knight who serves as the central hero of Shota Rustaveli’s medieval epic poem "The Knight in the Panther’s Skin."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5919c9c88190a2ddcf2cefee79a5 |
completed | April 27, 2026, 12:39 p.m. |
Created at: April 16, 2026, 6:36 p.m.