Triple

T3944192
Position Surface form Disambiguated ID Type / Status
Subject Dan Gilbert E92105 entity
Predicate founded P104 FINISHED
Object Quicken Loans E210124 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: Quicken Loans | Statement: [Dan Gilbert, founded, Quicken Loans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Quicken Loans
Context triple: [Dan Gilbert, founded, Quicken Loans]
  • A. Rocket Mortgage chosen
    Rocket Mortgage is a leading U.S.-based online mortgage lender known for its fully digital home loan application and approval process.
  • B. Countrywide Financial
    Countrywide Financial was a major U.S. mortgage lender heavily involved in subprime lending and central to the 2008 financial crisis before being taken over by Bank of America.
  • C. Capital One
    Capital One is a major American bank holding company best known for its credit card, auto loan, banking, and savings products.
  • D. CitiMortgage
    CitiMortgage is the home lending and mortgage services division of Citigroup, providing mortgage loans and related financial products to consumers.
  • E. Ameriquest Mortgage Company
    Ameriquest Mortgage Company was a major U.S. subprime mortgage lender that became emblematic of predatory lending practices and the excesses leading up to the 2008 financial crisis.
  • 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_69aed965502c8190904ebad1203a4ae8 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeee00d94881908fcf5ee1e27b1658 completed March 9, 2026, 3:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b53394eccc8190a58534e749e24b07 completed March 14, 2026, 10:08 a.m.
Created at: March 9, 2026, 3:24 p.m.