Triple

T13784507
Position Surface form Disambiguated ID Type / Status
Subject SoFi Technologies, Inc. E331218 entity
Predicate shortName P43 FINISHED
Object SoFi E331218 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: SoFi | Statement: [SoFi Technologies, Inc., shortName, SoFi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SoFi
Context triple: [SoFi Technologies, Inc., shortName, SoFi]
  • A. SoFi Technologies, Inc. chosen
    SoFi Technologies, Inc. is a U.S.-based online personal finance company offering services such as student loan refinancing, mortgages, investing, and banking products.
  • B. Capital One
    Capital One is a major American bank holding company best known for its credit card, auto loan, banking, and savings products.
  • C. Orange Bank
    Orange Bank is a French mobile-first digital bank offering online banking and financial services under the Orange telecommunications brand.
  • D. Wells Fargo
    Wells Fargo is a large American multinational financial services company and one of the biggest banks in the United States.
  • E. U.S. Bank
    U.S. Bank is a major American financial services company and one of the largest commercial banks in the United States.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0248db988190aa43c3723af25f90 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b07b0b2881909b316e3cc67f1ec1 completed May 3, 2026, 8:30 p.m.
Created at: April 9, 2026, 10:11 p.m.