Triple

T7461396
Position Surface form Disambiguated ID Type / Status
Subject Public Law 110-343 E176256 entity
Predicate authorizesSpendingLimit P7930 FINISHED
Object 700 billion U.S. 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: 700 billion U.S. dollars | Statement: [Public Law 110-343, authorizesSpendingLimit, 700 billion U.S. dollars]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: authorizesSpendingLimit
Context triple: [Public Law 110-343, authorizesSpendingLimit, 700 billion U.S. dollars]
  • A. authorizedSpending chosen
    Indicates that an entity has been granted permission to spend or allocate a specified amount of resources, typically funds, under defined conditions.
  • B. deficitLimit
    Indicates a constraint or maximum allowable amount on how large a deficit (shortfall or negative balance) may be.
  • C. moneyBillsRestriction
    Indicates a limitation or control placed on the use, amount, or handling of money bills in a given context.
  • D. isLimitOf
    Indicates that one quantity, function, or sequence approaches a particular value as its input or index approaches some specified point or condition.
  • E. supportsSpendingCategory
    Indicates that one entity allows, enables, or is compatible with making expenditures in a specified spending category.
  • 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_69c69f21632481908bf83f6c6da897e3 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f3d6cf8c8190a31cac121d151d78 completed March 27, 2026, 9:17 p.m.
PD Predicate disambiguation batch_69c6f03bad9c8190bdd5abb86d37df47 completed March 27, 2026, 9:01 p.m.
Created at: March 27, 2026, 3:38 p.m.