Triple
T4904147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tbilisi Metro |
E109873
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Marjanishvili |
E88467
|
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: Marjanishvili | Statement: [Tbilisi Metro, hasStation, Marjanishvili]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marjanishvili Context triple: [Tbilisi Metro, hasStation, Marjanishvili]
-
A.
Arsukidze
Arsukidze was a medieval Georgian architect renowned as the master builder of the Svetitskhoveli Cathedral in Mtskheta.
-
B.
Javakhishvili
Javakhishvili is a Georgian surname most notably associated with prominent figures such as writer Mikheil Javakhishvili.
-
C.
Robakidze
Robakidze is a Georgian surname most notably borne by the writer and public figure Grigol Robakidze.
-
D.
Mkhedruli
Mkhedruli is the modern Georgian script used for writing the Georgian language and several related Kartvelian languages.
-
E.
Kote Marjanishvili
chosen
Kote Marjanishvili was a prominent Georgian theater director and reformer, regarded as one of the founders of modern Georgian stage art.
- 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.