Triple

T6180053
Position Surface form Disambiguated ID Type / Status
Subject Royal Bank of Canada E137917 entity
Predicate hasPart P35 FINISHED
Object RBC Insurance E572899 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: RBC Insurance | Statement: [Royal Bank of Canada, hasPart, RBC Insurance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RBC Insurance
Context triple: [Royal Bank of Canada, hasPart, RBC Insurance]
  • A. RBC Insurance chosen
    RBC Insurance is the insurance division of the Royal Bank of Canada, offering a range of personal and business insurance products and services.
  • B. RBC
    RBC is a major Canadian multinational financial services company and one of the largest banks in North America by market capitalization.
  • C. Insuricare
    Insuricare is the fictional insurance company in Pixar's "The Incredibles" where Bob Parr (Mr. Incredible) works in a soul-crushing desk job.
  • D. Bankers Life and Casualty Company
    Bankers Life and Casualty Company is a major American insurance company best known for its life and health insurance products and for having been owned and expanded by businessman John D. MacArthur.
  • E. Esurance
    Esurance is a U.S.-based online-focused auto and home insurance company known for its direct-to-consumer model and digital tools for buying and managing policies.
  • 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_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c060fca4cc8190bf95231cd2a594c1 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16ef823348190a8ed68141857e28c completed March 23, 2026, 4:48 p.m.
Created at: March 22, 2026, 4:18 p.m.