Triple

T25433912
Position Surface form Disambiguated ID Type / Status
Subject Medicaid Drug Rebate Program E637326 entity
Predicate fundingFlow P73188 FINISHED
Object manufacturers pay rebates to states 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: manufacturers pay rebates to states | Statement: [Medicaid Drug Rebate Program, fundingFlow, manufacturers pay rebates to states]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fundingFlow
Context triple: [Medicaid Drug Rebate Program, fundingFlow, manufacturers pay rebates to states]
  • A. fundsFlowThrough chosen
    Indicates that financial resources are transferred or routed from one entity to another via an intermediate entity, account, or channel.
  • B. flowsUnder
    Indicates that one entity (typically a river, stream, or liquid) passes beneath another entity (such as a bridge, structure, or obstacle) along its course.
  • C. fundingContext
    Indicates the circumstances, purpose, or conditions under which funding is provided or used in a given relationship or action.
  • D. flowsAcross
    Indicates that one entity moves or extends in a continuous stream from one side of another entity to the other, traversing its area or boundary.
  • E. fundingSpeed
    Indicates how quickly financial resources are provided or disbursed within a given funding relationship or process.
  • F. None of above.

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_69e75db6c97081908178383fa632b193 completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69f5f6dd99f88190848a5bbee795aa17 completed May 2, 2026, 1:06 p.m.
PD Predicate disambiguation batch_69f4806d93dc8190b9dff4c63186faff completed May 1, 2026, 10:29 a.m.
Created at: April 21, 2026, 1:59 p.m.