Triple

T9800817
Position Surface form Disambiguated ID Type / Status
Subject Apple Card E237830 entity
Predicate creditBureau P30059 FINISHED
Object TransUnion E86595 NE FINISHED

How this triple was built (3 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: TransUnion | Statement: [Apple Card, creditBureau, TransUnion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TransUnion
Context triple: [Apple Card, creditBureau, TransUnion]
  • A. TransUnion chosen
    TransUnion is one of the three major U.S. credit reporting agencies, providing consumer credit reports, risk scores, and related financial data services to lenders and businesses worldwide.
  • B. Experian
    Experian is a global consumer credit reporting agency that collects and analyzes financial data to provide credit scores and related services to individuals and businesses.
  • C. Equifax
    Equifax is one of the three major U.S. credit reporting agencies, providing consumer credit information and related financial services worldwide.
  • D. Credit Karma
    Credit Karma is a personal finance company best known for offering free credit scores, credit monitoring, and tailored financial product recommendations to consumers.
  • E. Acxiom
    Acxiom is a global data and marketing technology company known for providing consumer data, analytics, and audience targeting solutions to businesses.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: creditBureau
Context triple: [Apple Card, creditBureau, TransUnion]
  • A. hasBureau chosen
    Indicates that an entity is associated with or possesses a specific bureau, such as an office, department, or administrative unit.
  • B. hasCreditRating
    Indicates that an entity is assigned a formal assessment of its creditworthiness, typically expressed as a credit score or rating.
  • C. hasCredit
    Indicates that an entity possesses or is assigned a credit, such as financial credit, academic credit, or acknowledgment for a contribution.
  • D. scoringReputation
    Indicates that one entity evaluates and assigns a reputation-related score to another entity based on its behavior or performance.
  • E. liveReputation
    Indicates a dynamic, continuously updated assessment of an entity’s standing, trustworthiness, or performance based on recent or real-time information.
  • F. None of above.

Provenance (4 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_69ca84dd4608819097ff4ed00feca280 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda62a11a88190880e0cce24923b14 completed April 1, 2026, 11:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c44a652c81908f644e1a5efe3eb1 completed April 5, 2026, 2:09 a.m.
PD Predicate disambiguation batch_69cd03da45a88190b71b1be3354c15a6 completed April 1, 2026, 11:39 a.m.
Created at: March 30, 2026, 8:29 p.m.