Triple
T2877012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerch Strait |
E56900
|
entity |
| Predicate | hasNearbyCity |
P350
|
FINISHED |
| Object | Kerch |
E11943
|
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: Kerch | Statement: [Kerch Strait, hasNearbyCity, Kerch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kerch Context triple: [Kerch Strait, hasNearbyCity, Kerch]
-
A.
Kerch
chosen
Kerch is a historic port city in eastern Crimea, strategically located on the Kerch Strait linking the Black Sea and the Sea of Azov.
-
B.
Sevastopolskaya
Sevastopolskaya is a Moscow Metro station serving the Serpukhovsko–Timiryazevskaya Line in the city’s southern part.
-
C.
Berdyansk
Berdyansk is a port city in southeastern Ukraine on the northern coast of the Sea of Azov, known for its maritime trade, beaches, and resort facilities.
-
D.
Simferopol–Alushta
Simferopol–Alushta is the central mountain-crossing section of the Crimean trolleybus route that links the regional capital Simferopol with the Black Sea resort town of Alushta.
-
E.
Yevpatoria
Yevpatoria is a historic resort and port city on the western coast of Crimea, known for its beaches, therapeutic mud treatments, and diverse cultural heritage.
- 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_69ab4a4ced288190ab6d3e062d10f7f6 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abe007329c8190b0bc1851c7307124 |
completed | March 7, 2026, 8:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b08648923c8190bd544177b825a494 |
completed | March 10, 2026, 8:59 p.m. |
Created at: March 6, 2026, 10:03 p.m.