Triple
T16801041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terioki |
E408352
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Primorsk |
E197493
|
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: Primorsk | Statement: [Terioki, nearbyCity, Primorsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Primorsk Context triple: [Terioki, nearbyCity, Primorsk]
-
A.
Primorsk
chosen
Primorsk is a port town in northwestern Russia situated on the coast of the Gulf of Finland in Leningrad Oblast.
-
B.
Primorsko
Primorsko is a Bulgarian Black Sea coastal town and resort known for its beaches and tourism, located in southeastern Bulgaria.
-
C.
Obdorsk
Obdorsk is the historical name of the Arctic city now known as Salekhard in northwestern Siberia, Russia.
-
D.
Svetlogorsk
Svetlogorsk is an industrial city in southeastern Belarus known for its chemical and pulp-and-paper industries along the Berezina River.
-
E.
Svetlogorsk
Svetlogorsk is a coastal resort town on the Baltic Sea in Russia’s Kaliningrad Oblast, known for its beaches, sanatoriums, and picturesque seaside promenade.
- 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_69d88393905081908d00a86b99996ac8 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2c826808190aa0a5bfcde2e49a8 |
completed | April 18, 2026, 4:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00ab1598dc81909fa5118e739a3291 |
completed | May 10, 2026, 3:58 p.m. |
Created at: April 10, 2026, 5:22 a.m.