Triple
T456651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgian script |
E7247
|
entity |
| Predicate | historicalVariant |
P4181
|
FINISHED |
| Object | Nuskhuri |
E7708
|
NE 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: Nuskhuri | Statement: [Georgian script, historicalVariant, Nuskhuri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nuskhuri Context triple: [Georgian script, historicalVariant, Nuskhuri]
-
A.
Nuskhuri
chosen
Nuskhuri is a medieval Georgian script primarily used in religious manuscripts and liturgical texts of the Georgian Orthodox Church.
-
B.
Hazaragi
Hazaragi is a variety of Persian primarily spoken by the Hazara people of central Afghanistan and surrounding regions, distinguished by its unique phonology and significant Turkic and Mongolic influences.
-
C.
Haya
Haya is a feminine given name of Arabic origin, commonly used in the Middle East and among Arabic-speaking communities.
-
D.
Asomtavruli
Asomtavruli is the oldest form of the Georgian script, characterized by its monumental, rounded letters historically used in inscriptions and religious manuscripts.
-
E.
Ishbak
Ishbak is a lesser-known son of the biblical patriarch Abraham, mentioned among the children he had later in life.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2f01ec5148190b74e1727712f1163 |
completed | Feb. 28, 2026, 1:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a44cbecca48190ab10a14ed0037339 |
completed | March 1, 2026, 2:27 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.