Triple
T18903137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Courland and Semigallia |
E462386
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Jelgava |
—
|
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: Jelgava | Statement: [Duke of Courland and Semigallia, hasCapital, Jelgava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jelgava Context triple: [Duke of Courland and Semigallia, hasCapital, Jelgava]
-
A.
Jelgava
chosen
Jelgava is a city in central Latvia known for its historic Jelgava Palace and role as a regional cultural and educational center.
-
B.
Ventspils
Ventspils is a port city on Latvia’s Baltic Sea coast known for its major ice-free harbor, oil and cargo terminals, and well-preserved historic center.
-
C.
Paldiski
Paldiski is a coastal town and former Soviet naval base in northwestern Estonia, located on the Pakri Peninsula by the Baltic Sea.
-
D.
Valmiera
Valmiera is a historic city in northern Latvia, situated on the Gauja River and known today as a regional economic and cultural center in the Vidzeme region.
-
E.
Jaunpils
Jaunpils is a small historic town in western Latvia known for its medieval castle and rural surroundings.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c52b07c08190be0db22826462ae3 |
completed | April 20, 2026, 6:18 a.m. |
Created at: April 10, 2026, 11:58 a.m.