Triple
T21456171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Azerbaijan |
E529344
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Yevlakh |
—
|
NE NERFINISHED |
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: Yevlakh | Statement: [Central Azerbaijan, hasCity, Yevlakh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yevlakh Context triple: [Central Azerbaijan, hasCity, Yevlakh]
-
A.
Yevlakh
chosen
Yevlakh is a city in central Azerbaijan that serves as an important regional transport and agricultural hub.
-
B.
Goychay
Goychay is a town in central Azerbaijan known today as the administrative center of the Goychay District and for its pomegranate cultivation and annual pomegranate festival.
-
C.
Khankendi
Khankendi is a city in the Nagorno-Karabakh region of the South Caucasus, internationally recognized as part of Azerbaijan and also known by its Armenian name Stepanakert.
-
D.
Gandzhachay
Gandzhachay is a river in western Azerbaijan that flows through the city of Ganja before joining the Kura River.
-
E.
Yaropolch
Yaropolch is a village in Russia historically noted as the place where Ukrainian Hetman Petro Doroshenko died.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9d6da3c819082a495f5434c5554 |
completed | April 23, 2026, 9:43 a.m. |
Created at: April 16, 2026, 6:08 p.m.