Triple
T21501022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirvanshahs |
E530473
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Shamakhi |
—
|
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: Shamakhi | Statement: [Shirvanshahs, capital, Shamakhi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shamakhi Context triple: [Shirvanshahs, capital, Shamakhi]
-
A.
Shamakhi
chosen
Shamakhi is a historic city in Azerbaijan known for its long-standing Jewish community and cultural significance in the region.
-
B.
Shamakhi Tat
Shamakhi Tat is a regional variety of the Southern Tat language traditionally spoken by Tat communities in and around the city of Shamakhi in Azerbaijan.
-
C.
Shirvan city
Shirvan city is an urban center in Azerbaijan located in the central lowland region along the Kura River, known for its role in regional industry and transportation.
-
D.
Aghjabadi
Aghjabadi is a town and administrative center in central Azerbaijan known for its agricultural economy and regional cultural significance.
-
E.
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.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea5be400819093e2b7e145254eab |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:24 p.m.