Triple

T7930978
Position Surface form Disambiguated ID Type / Status
Subject Flatiron Health E184186 entity
Predicate regulatoryEngagement P79837 FINISHED
Object supports submissions to the U.S. Food and Drug Administration 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 submissions to the U.S. Food and Drug Administration | Statement: [Flatiron Health, regulatoryEngagement, supports submissions to the U.S. Food and Drug Administration]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regulatoryEngagement
Context triple: [Flatiron Health, regulatoryEngagement, supports submissions to the U.S. Food and Drug Administration]
  • A. regulatoryResponse
    Indicates a reaction, decision, or adjustment made by a regulatory body in response to a particular event, condition, or entity’s behavior.
  • B. regulatoryAudience
    Indicates that something is intended for, directed toward, or relevant to a regulatory body or oversight authority as its audience.
  • C. associatedWithRegulation
    Indicates a relationship where something is linked to, governed by, or relevant to a specific regulation or regulatory framework.
  • D. regulationImpact
    Indicates how a regulation influences, constrains, or alters the behavior, performance, or outcomes associated with the related entities.
  • E. alsoRegulates
    Indicates that an entity not only has a primary regulatory effect on a target but additionally regulates that same target through another, supplementary regulatory relationship.
  • 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_69ca8290c21c8190906a5ca6fe2b03c4 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3accc388819087065ebe7d5d9591 completed March 31, 2026, 3:09 a.m.
PD Predicate disambiguation batch_69cae9335f288190ba96781fd6576a2b completed March 30, 2026, 9:20 p.m.
PDg Predicate description generation batch_69caf7882b048190baa333af9f698590 completed March 30, 2026, 10:22 p.m.
Created at: March 30, 2026, 5:07 p.m.