Triple
T12213618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rybinsk |
E291027
|
entity |
| Predicate | twinnedWith |
P1072
|
FINISHED |
| Object | Kovel |
E211354
|
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: Kovel | Statement: [Rybinsk, twinnedWith, Kovel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kovel Context triple: [Rybinsk, twinnedWith, Kovel]
-
A.
Kovel
chosen
Kovel is a historic town in northwestern Ukraine, located in the Volyn region and known as a former important railway and trade hub.
-
B.
Rumia
Rumia is a town in northern Poland, located near the Baltic coast and forming part of the Gdynia–Sopot–Gdańsk metropolitan area.
-
C.
Oziersk
Oziersk is a town in Russia’s Kaliningrad Oblast, historically linked to nearby Polish regions and engaged in cross-border cooperation with places like Gołdap.
-
D.
Küstrin
Küstrin is a historic town on the Oder River—now largely part of Kostrzyn nad Odrą in western Poland—that once belonged to Germany and served as a significant Prussian fortress and administrative center.
-
E.
Opava
Opava is a historic city in the Czech Republic’s Silesian region, known as a former political and cultural center of Silesia.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91c931cec819083ca19be06a33e1c |
completed | April 10, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6345e63dc81908f711dfb6d3b5a1f |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:51 p.m.