Triple
T13821948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Council Directive 92/43/EEC |
E332158
|
entity |
| Predicate | EULawArea |
P2167
|
FINISHED |
| Object | environmental protection |
—
|
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: environmental protection | Statement: [Council Directive 92/43/EEC, EULawArea, environmental protection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EULawArea Context triple: [Council Directive 92/43/EEC, EULawArea, environmental protection]
-
A.
appliesEUAcquisInField
Indicates that an entity implements or enforces the body of European Union law (the EU acquis) within a specific policy or regulatory field.
-
B.
EURLexSector
Indicates the legal or regulatory sector within the EUR-Lex classification system to which a given document or item is assigned.
-
C.
notableAreaOfLaw
Indicates that a person or entity is particularly recognized or distinguished in a specific field or area of law.
-
D.
legalArea
chosen
Indicates the specific field or branch of law that a legal matter, case, or document pertains to.
-
E.
relatedLegalSystem
Indicates that there is an association or connection between two legal systems, such as influence, similarity, shared origin, or mutual relevance.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0284428081908043c55caeefb833 |
completed | April 14, 2026, 9:01 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:12 p.m.