Triple

T5340525
Position Surface form Disambiguated ID Type / Status
Subject CRD E123932 entity
Predicate regulatorRole P63091 FINISHED
Object supports FINRA oversight of broker-dealers LITERAL 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: supports FINRA oversight of broker-dealers | Statement: [CRD, regulatorRole, supports FINRA oversight of broker-dealers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regulatorRole
Context triple: [CRD, regulatorRole, supports FINRA oversight of broker-dealers]
  • A. regulatorType
    Indicates the specific kind or category of regulatory role or authority associated with an entity.
  • B. primaryRegulator
    Indicates that one entity serves as the main controlling or governing authority over another entity or process.
  • C. regulatorEstablished
    Indicates that an entity has formally created, instituted, or set up a regulatory body or authority.
  • D. regulatorsInvolved
    Indicates that one or more regulatory authorities are involved in overseeing, reviewing, or influencing the referenced entity or activity.
  • E. regnalRole
    Indicates the specific official capacity or position a monarch holds or held during their reign.
  • F. None of above. chosen

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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85e86edc81908d87933db6489f91 completed March 20, 2026, 5:37 p.m.
PD Predicate disambiguation batch_69bd845a62b081909782863865b257a9 completed March 20, 2026, 5:31 p.m.
PDg Predicate description generation batch_69bd85e69e808190b29548670fd2900a completed March 20, 2026, 5:37 p.m.
Created at: March 20, 2026, 2 p.m.