Triple
T22738256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karosta |
E562333
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Karosta Prison |
—
|
NE NERFINISHED |
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: Karosta Prison | Statement: [Karosta, hasLandmark, Karosta Prison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karosta Prison Context triple: [Karosta, hasLandmark, Karosta Prison]
-
A.
Karosta Prison
chosen
Karosta Prison is a former military detention facility in Liepāja, Latvia, now operating as a museum and extreme tourism attraction known for its preserved Soviet-era prison conditions and immersive experiences.
-
B.
Sukeva Prison
Sukeva Prison is a Finnish correctional facility located in the village of Sukeva in northern Finland.
-
C.
Telemark Prison
Telemark Prison is a high-security Norwegian correctional facility known internationally for housing mass murderer Anders Behring Breivik.
-
D.
Kumla Prison
Kumla Prison is one of Sweden’s highest-security correctional facilities, known for housing some of the country’s most dangerous offenders.
-
E.
Doftana Prison
Doftana Prison was a notorious Romanian penitentiary used during the interwar and early communist periods to detain political prisoners, including future leader Nicolae Ceaușescu.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245513a5c81908d5cb471b4fc429d |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17971751081909253984429c8d178 |
completed | April 29, 2026, 3:22 a.m. |
Created at: April 17, 2026, 3:22 p.m.