Triple

T433080
Position Surface form Disambiguated ID Type / Status
Subject Rajya Sabha E9754 entity
Predicate canRecommendAmendmentsTo P9444 FINISHED
Object Money bills 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: Money bills | Statement: [Rajya Sabha, canRecommendAmendmentsTo, Money bills]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: canRecommendAmendmentsTo
Context triple: [Rajya Sabha, canRecommendAmendmentsTo, Money bills]
  • A. hasAmendments
    Indicates that one entity (such as a document, law, or agreement) includes or is associated with one or more modifications, changes, or additions made after its original creation.
  • B. canAmendBills chosen
    Indicates that an entity has the authority or ability to modify, revise, or propose changes to bills.
  • C. amendmentRequires
    Indicates that a particular amendment is necessary or must be applied in relation to another item, document, or condition.
  • D. amendmentCount
    Indicates the number of amendments that have been made to a given item, document, or entity.
  • E. constitutionalChange
    Indicates a formal modification, addition, or removal of provisions within a constitution or foundational legal framework.
  • 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_69a2e801e1d48190b505d1dd336b52ac completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ef084840819080653004b674cba8 completed Feb. 28, 2026, 1:35 p.m.
PD Predicate disambiguation batch_69a2edda55e88190b7c17ba94d7df1ce completed Feb. 28, 2026, 1:30 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.