Triple
T10987658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zakatala |
E259670
|
entity |
| Predicate | roadConnectionTo |
P9041
|
FINISHED |
| Object | Sheki |
E805774
|
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: Sheki | Statement: [Zakatala, roadConnectionTo, Sheki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheki Context triple: [Zakatala, roadConnectionTo, Sheki]
-
A.
Sheki
chosen
Sheki is a historic city in northwestern Azerbaijan, renowned for its preserved Silk Road-era architecture, caravanserais, and rich culinary traditions.
-
B.
Kizlyar
Kizlyar is a town in the Republic of Dagestan, Russia, known historically as a frontier settlement and trading center in the North Caucasus region.
-
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.
Vanadzor
Vanadzor is the third-largest city of Armenia, known as an industrial and cultural center in the country's northern Lori Province.
-
E.
Makhachkala
Makhachkala is the largest city and main political, economic, and cultural center of the Russian republic of Dagestan, located on the western shore of the Caspian 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d787b3c8388190be77e95d56979a7f |
completed | April 9, 2026, 11:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e344e9c66c81909163cea6aa9276e0 |
completed | April 18, 2026, 8:46 a.m. |
Created at: April 8, 2026, 9:24 p.m.