Triple
T4652718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kežmarok |
E102333
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Prešov Region |
E130151
|
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: Prešov Region | Statement: [Kežmarok, locatedIn, Prešov Region]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prešov Region Context triple: [Kežmarok, locatedIn, Prešov Region]
-
A.
Prešov Region
chosen
The Prešov Region is an administrative region in northeastern Slovakia known for its mountainous landscapes, historic towns, and proximity to the High Tatras.
-
B.
Trnava Region
Trnava Region is an administrative region in western Slovakia known for its historic towns, agricultural landscape, and proximity to the capital, Bratislava.
-
C.
Košice Region
Košice Region is an administrative region in eastern Slovakia that includes the city of Košice as its largest urban center.
-
D.
Banská Bystrica region
The Banská Bystrica region is a central Slovak area historically known as a key stronghold and focal point of anti-Nazi resistance during World War II.
-
E.
Trenčín Region
Trenčín Region is an administrative region in western Slovakia known for its historic towns, including the city of Trenčín, and its cultural and economic significance.
- 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_69bd43d71a308190afea7280841b0de8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd6314883481908f085a7af497b0d8 |
completed | March 20, 2026, 3:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be0374967c8190b77bcd3ea1c4d59d |
completed | March 21, 2026, 2:33 a.m. |
Created at: March 20, 2026, 1:14 p.m.