Triple

T8571038
Position Surface form Disambiguated ID Type / Status
Subject Aviva Canada E202925 entity
Predicate partOf P40 FINISHED
Object Aviva Group E744106 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: Aviva Group | Statement: [Aviva Canada, partOf, Aviva Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aviva Group
Context triple: [Aviva Canada, partOf, Aviva Group]
  • A. Aviva plc chosen
    Aviva plc is a major British multinational insurance company providing life, general, and health insurance services across numerous global markets.
  • B. Aviva Canada
    Aviva Canada is a major property and casualty insurance company operating across Canada as part of the global Aviva insurance group.
  • C. M&G plc
    M&G plc is a UK-based international savings and investment company offering asset management and insurance solutions to retail and institutional clients.
  • D. Munich Re
    Munich Re is a leading global reinsurance company based in Germany, known for providing risk management and insurance solutions worldwide.
  • E. Swiss Re
    Swiss Re is a leading global reinsurance company headquartered in Zurich, Switzerland, providing risk transfer and insurance solutions worldwide.
  • 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_69ca8327b0a881908606ff860713964d completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbea4223888190a56d9026ae0b9ec0 completed March 31, 2026, 3:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea88464b88190983e22e70bf38e63 completed April 2, 2026, 5:33 p.m.
Created at: March 30, 2026, 6:21 p.m.