Triple
T22121548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinburn |
E546682
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Ochakiv |
—
|
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: Ochakiv | Statement: [Kinburn, nearbyCity, Ochakiv]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ochakiv Context triple: [Kinburn, nearbyCity, Ochakiv]
-
A.
Ochakiv
chosen
Ochakiv is a port city in southern Ukraine on the Black Sea coast, historically significant as a strategic fortress and naval base controlling access to the Dnieper–Bug estuary.
-
B.
Orikhiv
Orikhiv is a frontline town in Ukraine’s Zaporizhzhia region that has become strategically important in the Russo-Ukrainian war.
-
C.
Katerynopil
Katerynopil is an urban-type settlement in central Ukraine that serves as a local administrative and cultural center within Cherkasy Oblast.
-
D.
Kamianets-Podilskyi
Kamianets-Podilskyi is a historic city in western Ukraine renowned for its well-preserved medieval old town and impressive fortress overlooking the Smotrych River canyon.
-
E.
Horokhiv
Horokhiv is a small town in western Ukraine known for its location within the historic Volyn region.
- 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_69e11e38b3848190ac3a4fa97d56e65a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1297e7e188190873924403421caa2 |
completed | April 28, 2026, 9:41 p.m. |
Created at: April 16, 2026, 8:31 p.m.