Triple
T4904172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tbilisi Metro |
E109873
|
entity |
| Predicate | connectsDistrict |
P2564
|
FINISHED |
| Object | Didube |
E478956
|
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: Didube | Statement: [Tbilisi Metro, connectsDistrict, Didube]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Didube Context triple: [Tbilisi Metro, connectsDistrict, Didube]
-
A.
Didube
chosen
Didube is a metro station in Tbilisi, Georgia, serving as a key transit hub that connects the city’s metro system with major bus and marshrutka routes to other regions.
-
B.
Jebba
Jebba is a town in western Nigeria known for its strategic location on the Niger River and its historic bridge linking northern and southern Nigeria.
-
C.
Dschubba
Dschubba is a bright multiple star system that forms the "head" of the constellation Scorpius and is designated Delta Scorpii.
-
D.
Kibibi
Kibibi is a lively and energetic host character in Disney's "Festival of the Lion King" stage show at Disney theme parks.
-
E.
Hadibu
Hadibu is the main town and administrative center of the Yemeni island of Socotra in the Arabian Sea.
- 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.