Triple

T16199793
Position Surface form Disambiguated ID Type / Status
Subject Prague commuter rail E393166 entity
Predicate connectsTo P845 FINISHED
Object Milovice E249390 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: Milovice | Statement: [Prague commuter rail, connectsTo, Milovice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milovice
Context triple: [Prague commuter rail, connectsTo, Milovice]
  • A. Milovice chosen
    Milovice is a town in the Czech Republic known for its rapid post-military redevelopment and location northeast of Prague in the Central Bohemian Region.
  • B. Mikulov
    Mikulov is a historic wine-producing town in the South Moravian region of the Czech Republic, known for its chateau, picturesque old town, and proximity to the Pálava Hills.
  • C. Blovice
    Blovice is a small town in the Czech Republic that serves as a local administrative and service center in the Plzeň Region.
  • D. Lovosice
    Lovosice is a town in the Czech Republic, historically notable as the site of the 1756 Battle of Lobositz during the Seven Years' War.
  • E. Hlušovice
    Hlušovice is a small municipality and village in the Olomouc Region of the Czech Republic.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222de2db481908471b9c73d444607 completed April 17, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0075856f1881908548579b241e8009 completed May 10, 2026, 12:09 p.m.
Created at: April 10, 2026, 5:03 a.m.