Triple
T22848166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karosta Prison |
E566279
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Liepāja port |
—
|
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: Liepāja port | Statement: [Karosta Prison, near, Liepāja port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liepāja port Context triple: [Karosta Prison, near, Liepāja port]
-
A.
Port of Liepāja
chosen
The Port of Liepāja is a major ice-free Baltic Sea port in western Latvia that serves as an important regional hub for cargo handling, industry, and maritime transport.
-
B.
Port of Riga
The Port of Riga is a major Baltic Sea seaport in Latvia that serves as a key hub for regional trade, cargo transit, and passenger traffic.
-
C.
Port of Ventspils
The Port of Ventspils is one of Latvia’s major ice-free Baltic Sea ports, serving as a key hub for cargo transit and maritime trade in the region.
-
D.
Baltiysk seaport
Baltiysk seaport is a major Russian Baltic Sea port and naval base located near the Vistula Spit in the Kaliningrad Oblast.
-
E.
Jūrmala
Jūrmala is a popular Latvian resort city on the Gulf of Riga, known for its long sandy beaches, wooden architecture, and spa traditions.
- 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e89ab348190a31260221195ae67 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:36 p.m.