Triple
T9977051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaporizhian Sich |
E196357
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Bazavluk Sich |
E834057
|
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: Bazavluk Sich | Statement: [Zaporizhian Sich, capital, Bazavluk Sich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bazavluk Sich Context triple: [Zaporizhian Sich, capital, Bazavluk Sich]
-
A.
Dzyarzhynskaya Hara
Dzyarzhynskaya Hara is the tallest hill in Belarus, known as the country’s highest natural elevation.
-
B.
Tomakivka Sich
chosen
Tomakivka Sich was one of the principal fortified Cossack strongholds of the Zaporizhian Host in what is now Ukraine.
-
C.
Pishpek fortress
Pishpek fortress was a Russian Imperial military outpost in Central Asia that gave its name to the settlement that later became Bishkek, the capital of Kyrgyzstan.
-
D.
Maloyaroslavets
Maloyaroslavets is a historic town in western Russia known for the 1812 Battle of Maloyaroslavets during Napoleon’s invasion.
-
E.
Ust-Dzheguta
Ust-Dzheguta is a town in the Karachay-Cherkess Republic of southwestern Russia, situated in the North Caucasus region.
- 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_69ca82eea2b88190a0e511d21a31f386 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb84d0d3c8190b268582bb79c8973 |
completed | April 2, 2026, 12:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26a08a60c81909be30a442787328b |
completed | April 5, 2026, 1:56 p.m. |
Created at: March 30, 2026, 8:48 p.m.