Triple
T15423541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berdychiv |
E369445
|
entity |
| Predicate | connectedByRailTo |
P848
|
FINISHED |
| Object | Koziatyn |
E693342
|
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: Koziatyn | Statement: [Berdychiv, connectedByRailTo, Koziatyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koziatyn Context triple: [Berdychiv, connectedByRailTo, Koziatyn]
-
A.
Koziatyn
chosen
Koziatyn is a small city in central Ukraine known as a local railway junction and administrative center within Vinnytsia Oblast.
-
B.
Radomyshl
Radomyshl is a historic town in northern Ukraine, known for its Jewish heritage and role within the Zhytomyr Oblast region.
-
C.
Tarnopol
Tarnopol is a historic city in western Ukraine, now known as Ternopil, which has long served as a regional cultural and administrative center.
-
D.
Kraśnik
Kraśnik is a town in eastern Poland known for its historical architecture and location within the Lublin region.
-
E.
Horodok
Horodok is a small town in western Ukraine known for its historical roots and location within the Khmelnytskyi 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ec032548190840b558dde6057c7 |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a7d02a08190a1e34e3a014acea9 |
completed | May 9, 2026, 11:29 a.m. |
Created at: April 10, 2026, 3:20 a.m.