Triple

T106062
Position Surface form Disambiguated ID Type / Status
Subject Supreme Court of Japan E2138 entity
Predicate reviewsConstitutionalityOf P1122 FINISHED
Object laws 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: laws | Statement: [Supreme Court of Japan, reviewsConstitutionalityOf, laws]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: reviewsConstitutionalityOf
Context triple: [Supreme Court of Japan, reviewsConstitutionalityOf, laws]
  • A. constitutionalChallenge chosen
    Indicates a legal action or argument asserting that a law, policy, or governmental act violates a constitution and should be reviewed or invalidated.
  • B. constitutionalNumber
    Indicates that an entity has a specific number or count defined or constrained by a constitution or foundational governing document.
  • C. constitutionalContext
    Indicates that something occurs, is interpreted, or is evaluated within the framework, principles, or provisions of a constitution.
  • D. constitutionalCategory
    Indicates the classification of something according to its constitutional or structural type or category.
  • E. constitutionalCitation
    Indicates a relationship where one entity cites, references, or is grounded in a specific provision or article of a constitution.
  • 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_69a24e0a5b7c81908d52da08c60dabc4 completed Feb. 28, 2026, 2:08 a.m.
NER Named-entity recognition batch_69a256ec650c8190bee2067e37065527 completed Feb. 28, 2026, 2:46 a.m.
PD Predicate disambiguation batch_69a2563d33788190999d471b486d5603 completed Feb. 28, 2026, 2:43 a.m.
Created at: Feb. 28, 2026, 2:12 a.m.