Triple
T35143028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Article 15(5) |
E1014746
|
entity |
| Predicate | derogationFrom |
P3077
|
FINISHED |
| Object | formal equality principle under Article 15(1) |
—
|
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: formal equality principle under Article 15(1) | Statement: [Article 15(5), derogationFrom, formal equality principle under Article 15(1)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: derogationFrom Context triple: [Article 15(5), derogationFrom, formal equality principle under Article 15(1)]
-
A.
derogatesFrom
chosen
Indicates that one entity diminishes, belittles, or detracts from the value, reputation, or importance of another entity.
-
B.
derogadaPor
Indicates that a law, rule, or norm has been annulled, revoked, or rendered invalid by another legal provision or authority.
-
C.
nonDerogation
Indicates that the existence or exercise of one right, obligation, or provision does not diminish, restrict, or invalidate another.
-
D.
denialBy
Indicates that one entity refuses, rejects, or withholds approval, support, or a requested action from another entity.
-
E.
demotes
Indicates that one entity reduces another entity’s rank, status, or level within a hierarchy or system.
- 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_69f76dda7c108190a2ffd93eb6c341a7 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78cab90cc8190827145ac515d203b |
completed | May 3, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.