Triple
T1610646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microsoft Azure |
E34605
|
entity |
| Predicate | supportsComplianceStandard |
P24194
|
FINISHED |
| Object | GDPR |
E84602
|
NE 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: GDPR | Statement: [Microsoft Azure, supportsComplianceStandard, GDPR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GDPR Context triple: [Microsoft Azure, supportsComplianceStandard, GDPR]
-
A.
GDPR
chosen
The GDPR (General Data Protection Regulation) is a comprehensive European Union data protection law that governs how organizations collect, process, and store personal data of individuals in the EU.
-
B.
CCPA
CCPA (California Consumer Privacy Act) is a California state law that grants consumers enhanced rights over their personal data and imposes transparency and data-handling obligations on businesses.
-
C.
European Data Protection Supervisor
The European Data Protection Supervisor is the independent EU authority responsible for overseeing the protection of personal data and privacy within European Union institutions and bodies.
-
D.
ISO/IEC 27018
ISO/IEC 27018 is an international standard that provides guidelines and controls for protecting personally identifiable information (PII) in public cloud computing environments.
-
E.
Intelligent Tracking Prevention
Intelligent Tracking Prevention is a Safari privacy technology that uses machine learning to limit cross-site tracking and reduce advertisers’ ability to follow users across the web.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a885ffc5ec819091afa325d5f9611c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa61df32a88190a7e823a77bdcc84a |
completed | March 6, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad51c4bbfc8190b9d00e1562155a5f |
completed | March 8, 2026, 10:39 a.m. |
Created at: March 4, 2026, 7:28 p.m.