Triple
T2106503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Czech Army |
E42406
|
entity |
| Predicate | garrison |
P75
|
FINISHED |
| Object | Prague |
E14162
|
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: Prague | Statement: [Czech Army, garrison, Prague]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prague Context triple: [Czech Army, garrison, Prague]
-
A.
Prague
chosen
Prague is the historic capital city of the Czech Republic, renowned for its well-preserved medieval architecture, iconic Charles Bridge and Prague Castle, and vibrant cultural life.
-
B.
Kolín
Kolín is a historic industrial town and important transport hub on the Elbe River in the Central Bohemian Region of the Czech Republic.
-
C.
Brno
Brno is the second-largest city in the Czech Republic, known as a major cultural, educational, and industrial center in the historical region of Moravia.
-
D.
Liberec
Liberec is a city in the northern Czech Republic known for its textile industry heritage, mountainous surroundings, and the landmark Ještěd Tower.
-
E.
Plzeň
Plzeň is a major city in western Bohemia in the Czech Republic, known for its brewing tradition and industrial 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_69a8871040f08190aac2e2d0ab6b47ad |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbaddeb148190b728bce7a7b041fb |
completed | March 7, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af90470e908190961ac799f23af12f |
completed | March 10, 2026, 3:30 a.m. |
Created at: March 4, 2026, 7:43 p.m.