Triple

T27465994
Position Surface form Disambiguated ID Type / Status
Subject Data Protection Commissioner v Facebook Ireland and Maximillian Schrems E693178 entity
Predicate relatesToLaw P142158 FINISHED
Object General Data Protection Regulation 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: General Data Protection Regulation | Statement: [Data Protection Commissioner v Facebook Ireland and Maximillian Schrems, relatesToLaw, General Data Protection Regulation]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relatesToLaw
Context triple: [Data Protection Commissioner v Facebook Ireland and Maximillian Schrems, relatesToLaw, General Data Protection Regulation]
  • A. hasRelationshipToLaw chosen
    Indicates that one entity has a defined connection, relevance, or applicability to a specific law or legal framework.
  • B. legalCaseRelatedTo
    Indicates that there is a relevant connection or association between a legal case and another entity, such as a person, organization, event, or legal matter.
  • C. relatedLegalConcept
    Indicates that one legal concept is connected or associated with another through a relevant legal relationship or context.
  • D. relatedLawDiscoveredBy
    Indicates that a particular law is identified as having been discovered or formulated by a specific agent (such as a person or organization).
  • E. linkedLaw
    Indicates that there is a connection or reference between an entity and a specific law or legal provision.
  • 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_69ef538105548190a771cc5a0cf8c211 completed April 27, 2026, 12:16 p.m.
NER Named-entity recognition batch_69ff6ef0d61c81909162d37c15a1a3c3 completed May 9, 2026, 5:29 p.m.
PD Predicate disambiguation batch_69ff6c6a58e08190921317062cd9d489 completed May 9, 2026, 5:18 p.m.
Created at: April 27, 2026, 12:52 p.m.