Triple
T16471654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Georgian |
E400076
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Tao-Klarjeti |
E466618
|
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: Tao-Klarjeti | Statement: [Old Georgian, region, Tao-Klarjeti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tao-Klarjeti Context triple: [Old Georgian, region, Tao-Klarjeti]
-
A.
Tao-Klarjeti
chosen
Tao-Klarjeti is a medieval Georgian historical region known as a major political, cultural, and religious center of early Georgian statehood and Christian monastic life.
-
B.
Tao-Rusyr
Tao-Rusyr is a stratovolcano forming the southern volcanic massif of Onekotan Island in Russia’s Kuril Islands chain.
-
C.
Ta-Ha
Ta-Ha is a chapter (Surah 20) of the Qur’an known for its eloquent narration of the stories of prophets—especially Moses—and its themes of divine guidance, mercy, and spiritual reflection.
-
D.
T'ao
T'ao is an alternative transliteration of the Chinese name "Tao," commonly used in older or Wade–Giles romanization systems.
-
E.
Tigana
Tigana is a French former professional footballer and manager, best known as a dynamic midfielder for clubs like Bordeaux and the French national team during the 1980s.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32dd19df881909e4562a5e8473338 |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f5d16008190bd874080e86b8a2f |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:11 a.m.