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.