Triple

T6740850
Position Surface form Disambiguated ID Type / Status
Subject Aviva E154074 entity
Predicate brand P1500 FINISHED
Object Aviva Canada E202925 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 Canada | Statement: [Aviva, brand, Aviva Canada]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aviva Canada
Context triple: [Aviva, brand, Aviva Canada]
  • A. Aviva Canada chosen
    Aviva Canada is a major property and casualty insurance company operating across Canada as part of the global Aviva insurance group.
  • B. Sun Life Financial
    Sun Life Financial is a Canadian-based international financial services company best known for its life insurance, wealth management, and retirement solutions.
  • C. CIBC
    CIBC is one of Canada’s largest chartered banks, offering a wide range of financial services including personal, business, and investment banking.
  • D. Scotiabank
    Scotiabank is one of Canada's largest multinational banks, offering a wide range of financial services across the Americas and other global markets.
  • E. Rogers Bank
    Rogers Bank is a Canadian financial institution owned by Rogers Communications that focuses primarily on consumer credit card and payment products.
  • 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_69c6880d84d8819095d19de2295f26ac completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d18971e081908372cd25d52a11bd completed March 27, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70b0fb79c8190ae9871b7b2d9d733 completed March 27, 2026, 10:56 p.m.
Created at: March 27, 2026, 2:10 p.m.