Triple

T29651479
Position Surface form Disambiguated ID Type / Status
Subject Kennedy tax cut E750144 entity
Predicate federalLawIn P146487 FINISHED
Object United States NE NERFINISHED

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: United States | Statement: [Kennedy tax cut, federalLawIn, United States]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: federalLawIn
Context triple: [Kennedy tax cut, federalLawIn, United States]
  • A. federalLawContext
    Indicates that the relationship or action occurs within, is governed by, or is interpreted according to federal law or a federal legal framework.
  • B. federalStatute chosen
    Indicates that the relationship involves or is governed by a law enacted at the national (federal) level, as opposed to state or local law.
  • C. federalLawRepresentedBy
    Indicates that a federal law is formally presented, advocated, or sponsored by a particular representative or legal entity.
  • D. federalLawAppliesFrom
    Indicates that a specified federal law becomes effective or governs starting from a particular point in time or jurisdictional context.
  • E. federalLawsImplementedBy
    Indicates that certain federal laws are put into effect, enforced, or carried out by a specified implementing entity.
  • 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_69f0d6226fe881908819197c9ef9ee04 completed April 28, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f68a16debc8190a12f5f65ced055d7 completed May 2, 2026, 11:34 p.m.
PD Predicate disambiguation batch_69f6860def1c81909d79e1f088c4b5e5 completed May 2, 2026, 11:17 p.m.
Created at: April 28, 2026, 6:52 p.m.