Triple

T23519037
Position Surface form Disambiguated ID Type / Status
Subject M&S Bank E574450 entity
Predicate tradesAs P10476 FINISHED
Object M&S Bank 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: M&S Bank | Statement: [M&S Bank, tradesAs, M&S Bank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: M&S Bank
Context triple: [M&S Bank, tradesAs, M&S Bank]
  • A. M&S Bank chosen
    M&S Bank is a UK-based retail bank offering personal finance products and services under the Marks & Spencer brand.
  • B. Marine Midland Bank
    Marine Midland Bank was a major U.S. commercial bank based in Buffalo, New York, that became one of the largest regional banks in the Northeast before being acquired and rebranded by HSBC.
  • C. Mavis Bank
    Mavis Bank is a rural community in Jamaica known for its high-altitude coffee farming and production of the renowned Blue Mountain coffee.
  • D. Tesco Bank
    Tesco Bank is a UK-based retail bank offering personal finance products and services, operated under the Tesco supermarket brand.
  • E. Midland Bank
    Midland Bank was a major British commercial bank, historically one of the UK’s “Big Four,” later acquired by HSBC.
  • 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_69e245bb3dcc8190ba9a2b35972b58d0 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa84fe7c8190aa1078a118af7d61 completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:08 p.m.