Triple

T21128633
Position Surface form Disambiguated ID Type / Status
Subject FAST Act E520623 entity
Predicate authorizesSpending P10367 FINISHED
Object over 300 billion US dollars 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: over 300 billion US dollars | Statement: [FAST Act, authorizesSpending, over 300 billion US dollars]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: authorizesSpending
Context triple: [FAST Act, authorizesSpending, over 300 billion US dollars]
  • A. authorizedSpending
    Indicates that an entity has been granted permission to spend or allocate a specified amount of resources, typically funds, under defined conditions.
  • B. overseesSpendingOf
    Indicates that one entity has authority to monitor, direct, or control how another entity’s funds or budget are used.
  • C. supportsSpendingCategory
    Indicates that one entity allows, enables, or is compatible with making expenditures in a specified spending category.
  • D. authorizesFundingFor chosen
    Indicates that one entity grants official approval or permission for financial resources to be provided to another entity or purpose.
  • E. authorizedBudget
    Indicates that a specified budget amount has been formally approved for use by or for a particular entity or purpose.
  • 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7223a7a588190a01a66921b79b98b completed April 21, 2026, 7:07 a.m.
PD Predicate disambiguation batch_69e5f5ed6c8c8190b31092a5d4c3de5d completed April 20, 2026, 9:46 a.m.
Created at: April 16, 2026, 2:56 p.m.