Triple

T15966655
Position Surface form Disambiguated ID Type / Status
Subject Marcus by Goldman Sachs E387207 entity
Predicate hasCompetitor P1375 FINISHED
Object Discover Bank E237828 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: Discover Bank | Statement: [Marcus by Goldman Sachs, hasCompetitor, Discover Bank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Discover Bank
Context triple: [Marcus by Goldman Sachs, hasCompetitor, Discover Bank]
  • A. Discover Bank chosen
    Discover Bank is a U.S.-based online-focused bank known for offering credit cards, deposit accounts, and other consumer banking services under the Discover Financial Services umbrella.
  • B. Discovery Bank
    Discovery Bank is a submarine geological feature located on the Scotia Plate in the Southern Ocean.
  • C. Orange Bank
    Orange Bank is a French mobile-first digital bank offering online banking and financial services under the Orange telecommunications brand.
  • D. FirstBank
    FirstBank is a financial institution whose naming rights sponsorship extends to major venues such as FirstBank Stadium.
  • E. Ameris Bank
    Ameris Bank is a regional financial institution based in the southeastern United States, offering a range of banking and financial services to individuals and businesses.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15726536881908b603e43ae1acafb completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe87149081909ac6129126f597c2 completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:54 a.m.