Triple

T20803783
Position Surface form Disambiguated ID Type / Status
Subject FINRA CRD E512104 entity
Predicate relatedSystem P37 FINISHED
Object BrokerCheck 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: BrokerCheck | Statement: [FINRA CRD, relatedSystem, BrokerCheck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BrokerCheck
Context triple: [FINRA CRD, relatedSystem, BrokerCheck]
  • A. BrokerCheck chosen
    BrokerCheck is an online tool that provides background information on brokerage firms and financial advisors to help investors research their professional history and regulatory records.
  • B. Uphold
    Uphold is a multi-asset digital money platform that lets users buy, hold, and exchange cryptocurrencies, fiat currencies, and other assets through a unified account.
  • C. SPIN verification tool
    The SPIN verification tool is a widely used open-source model checker for detecting logical design errors in concurrent and distributed software systems.
  • D. Trustmark
    Trustmark is a U.S.-based financial services and employee benefits company known for providing health, wellness, and insurance solutions to employers and individuals.
  • E. ReputationDefender
    ReputationDefender is an online reputation management service that helps individuals and businesses monitor, protect, and improve their digital presence and search results.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2b2d5688190aaa58a2594d4787c completed April 21, 2026, 12:20 a.m.
Created at: April 16, 2026, 12:39 p.m.