Triple

T8799831
Position Surface form Disambiguated ID Type / Status
Subject London Marathon E209376 entity
Predicate formerSponsor P18226 FINISHED
Object Virgin Money E39795 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: Virgin Money | Statement: [London Marathon, formerSponsor, Virgin Money]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Virgin Money
Context triple: [London Marathon, formerSponsor, Virgin Money]
  • A. Virgin Money chosen
    Virgin Money is a UK-based financial services company offering banking and related products under Richard Branson’s Virgin brand.
  • B. First Direct
    First Direct is a UK-based telephone and online retail bank known for pioneering 24-hour, branchless banking services.
  • C. Barclaycard
    Barclaycard is a major British credit card and payment services brand owned by Barclays, known for its widespread consumer and business financial products and past high-profile sports sponsorships.
  • D. M&S Bank
    M&S Bank is a UK-based retail bank offering personal finance products and services under the Marks & Spencer brand.
  • E. N26
    N26 is a German digital bank and fintech company offering app-based banking services across multiple European markets.
  • 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_69ca836320e48190b5cf585b90a322c4 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fb7491c8190bcdb98d6cc003d9e completed March 31, 2026, 11:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6f658f248190957eba821b07cc4f completed April 3, 2026, 7:42 a.m.
Created at: March 30, 2026, 6:44 p.m.