Triple

T4054726
Position Surface form Disambiguated ID Type / Status
Subject Singapore law E84665 entity
Predicate hasConstitutionalReview P53035 FINISHED
Object judicial review 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: judicial review | Statement: [Singapore law, hasConstitutionalReview, judicial review]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasConstitutionalReview
Context triple: [Singapore law, hasConstitutionalReview, judicial review]
  • A. hasConstitutionalDoctrine
    Indicates that an entity is associated with, based on, or governed by a particular constitutional doctrine or set of constitutional principles.
  • B. containsConstitutionalCourt
    Indicates that one entity includes or has within it a constitutional court as part of its structure or jurisdiction.
  • C. isConstitutionalAuthority
    Indicates that an entity holds recognized legal or institutional power derived from or defined by a constitution.
  • D. hasConstitutionalBasisIn
    Indicates that something derives its legal authority, justification, or foundation from a specific constitutional provision or framework.
  • E. hasConstitutionalStatus
    Indicates that an entity possesses a particular status, role, or recognition as defined or protected by a constitution or constitutional framework.
  • F. None of above. chosen

Provenance (4 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_69aed933bec881909edfa28ebb69c634 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbaa84b88190856e179266769e6d completed March 9, 2026, 4:56 p.m.
PD Predicate disambiguation batch_69aef90249e4819095e9e043bc4aa9a6 completed March 9, 2026, 4:44 p.m.
PDg Predicate description generation batch_69aef9fcb31c819098d5287b6fc84f4e completed March 9, 2026, 4:49 p.m.
Created at: March 9, 2026, 3:38 p.m.