Triple
T135001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Charter for Regional or Minority Languages |
E2728
|
entity |
| Predicate | monitoringMechanism |
P752
|
FINISHED |
| Object | Committee of Experts of the European Charter for Regional or Minority Languages |
E15953
|
NE FINISHED |
How this triple was built (3 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: Committee of Experts of the European Charter for Regional or Minority Languages | Statement: [European Charter for Regional or Minority Languages, monitoringMechanism, Committee of Experts of the European Charter for Regional or Minority Languages]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Committee of Experts of the European Charter for Regional or Minority Languages Context triple: [European Charter for Regional or Minority Languages, monitoringMechanism, Committee of Experts of the European Charter for Regional or Minority Languages]
-
A.
Committee of Experts of the European Charter for Regional or Minority Languages
chosen
The Committee of Experts of the European Charter for Regional or Minority Languages is an independent monitoring body that evaluates how states implement the Charter’s protections for regional and minority languages and advises the Council of Europe on compliance.
-
B.
European Charter for Regional or Minority Languages
The European Charter for Regional or Minority Languages is a Council of Europe treaty aimed at protecting and promoting historical regional and minority languages across member states.
-
C.
Framework Convention for the Protection of National Minorities
The Framework Convention for the Protection of National Minorities is a Council of Europe treaty that sets legally binding standards for the protection of the rights, identity, and participation of national minority groups within member states.
-
D.
Council of Europe
The Council of Europe is a pan-European intergovernmental organization focused on promoting human rights, democracy, and the rule of law across its member states.
-
E.
European Roma Rights Centre
The European Roma Rights Centre is an international public interest law organization that combats anti-Roma racism and human rights violations through strategic litigation, advocacy, and research.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monitoringMechanism Context triple: [European Charter for Regional or Minority Languages, monitoringMechanism, Committee of Experts of the European Charter for Regional or Minority Languages]
-
A.
monitors
chosen
Indicates that one entity observes, tracks, or checks the state, behavior, or performance of another entity over time.
-
B.
securityMechanism
Indicates a relationship where one entity serves as a means or method to protect another entity from threats, vulnerabilities, or unauthorized actions.
-
C.
removalMechanism
Indicates the method or process by which something is removed, eliminated, or taken away from a system or context.
-
D.
hasCheckAndBalanceFunction
Indicates that one entity performs a checking or limiting role on another entity’s powers, providing oversight and balance within a system.
-
E.
transitionMechanismUsedWith
Indicates that a particular transition or change from one state to another is carried out using a specified mechanism or method.
- F. None of above.
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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257a3ad908190b6a8652f09ae0cbb |
completed | Feb. 28, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2b4bad1a0819098459e2a9d6b8d2a |
completed | Feb. 28, 2026, 9:26 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.