Triple

T19374601
Position Surface form Disambiguated ID Type / Status
Subject Komerční banka E484633 entity
Predicate hasSubsidiary P254 FINISHED
Object Komerční pojišťovna 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: Komerční pojišťovna | Statement: [Komerční banka, hasSubsidiary, Komerční pojišťovna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Komerční pojišťovna
Context triple: [Komerční banka, hasSubsidiary, Komerční pojišťovna]
  • A. Česká podnikatelská pojišťovna chosen
    Česká podnikatelská pojišťovna is a Czech insurance company providing a range of insurance products to individuals and businesses.
  • B. Oščadnica
    Oščadnica is a Slovak village in the Kysuce region known as a major mountain and ski resort destination.
  • C. Metrópolis Seguros
    Metrópolis Seguros is a Spanish insurance company best known for owning the iconic Edificio Metrópolis in Madrid.
  • D. Elite Insurance Company
    Elite Insurance Company is a Canadian insurance provider operating as a subsidiary of Aviva Canada, offering specialized property and casualty insurance products.
  • E. Komerční banka
    Komerční banka is one of the largest commercial banks in the Czech Republic, offering a wide range of retail, corporate, and investment banking services.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e61a5acc4481908fecfb57af16d037 completed April 20, 2026, 12:21 p.m.
Created at: April 10, 2026, 1:35 p.m.