Triple
T809321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adjara |
E17508
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Batumi |
E41677
|
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: Batumi | Statement: [Adjara, capital, Batumi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Batumi Context triple: [Adjara, capital, Batumi]
-
A.
Batumi
chosen
Batumi is a major Black Sea resort city in southwestern Georgia known for its beaches, modern skyline, and role as a regional economic and cultural hub.
-
B.
Tbilisi
Tbilisi is the largest city and cultural, political, and economic center of Georgia, located on the banks of the Kura River in the South Caucasus.
-
C.
Zugdidi
Zugdidi is a city in western Georgia that serves as the main urban and administrative center of the Samegrelo region.
-
D.
Tskhinvali
Tskhinvali is the capital city of the breakaway region of South Ossetia in the South Caucasus, serving as its political and administrative center.
-
E.
Rustavi
Rustavi is an industrial city in southeastern Georgia, located near the capital Tbilisi and known for its steel production and Soviet-era urban planning.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab256cbc8190bf75b5d5e35ff0aa |
completed | March 1, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac7f211bf88190bd6f791894ece41a |
completed | March 7, 2026, 7:40 p.m. |
Created at: March 1, 2026, 7:38 p.m.