Triple
T4904170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tbilisi Metro |
E109873
|
entity |
| Predicate | connectsDistrict |
P2564
|
FINISHED |
| Object | Varketili |
E478957
|
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: Varketili | Statement: [Tbilisi Metro, connectsDistrict, Varketili]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Varketili Context triple: [Tbilisi Metro, connectsDistrict, Varketili]
-
A.
Varketili
chosen
Varketili is a metro station in Tbilisi, Georgia, serving as a key terminus on the Tbilisi Metro network.
-
B.
Veltro
Veltro is the nickname of the Macchi C.205, an Italian World War II fighter aircraft renowned for its speed and agility.
-
C.
Tsilivi
Tsilivi is a popular seaside resort village on the Greek island of Zakynthos, known for its sandy beach, family-friendly atmosphere, and vibrant tourist facilities.
-
D.
Garliava
Garliava is a small town in central Lithuania known as a suburban community near the city of Kaunas.
-
E.
Vlichos
Vlichos is a small coastal village on the Greek island of Hydra, known for its traditional stone houses, quiet beaches, and scenic seaside promenade.
- 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_69bd441180708190ba42ffb44fea533a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e6fdeac81909092f51ae40ad20e |
completed | March 20, 2026, 3:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be779c47348190bd8e19f87c2aa4c2 |
completed | March 21, 2026, 10:49 a.m. |
Created at: March 20, 2026, 1:29 p.m.