Triple
T35378537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simmenthal |
E1022580
|
entity |
| Predicate | reinforcesCaseLaw |
P129583
|
FINISHED |
| Object | Costa v ENEL |
—
|
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: Costa v ENEL | Statement: [Simmenthal, reinforcesCaseLaw, Costa v ENEL]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reinforcesCaseLaw Context triple: [Simmenthal, reinforcesCaseLaw, Costa v ENEL]
-
A.
legalReformer
Indicates that an entity works to change, improve, or modernize laws or legal systems.
-
B.
legalPrecedentInvolved
Indicates that a particular legal precedent (prior court decision or ruling) is relevant to, cited in, or forms the basis for the current legal matter or action.
-
C.
stateOfLaw
Indicates that a specified legal condition, rule, or status is currently in force or applicable within a given jurisdiction or context.
-
D.
legalPrecedentFrom
Indicates that a legal decision, ruling, or principle is derived from, based on, or justified by an earlier legal case or authority.
-
E.
usesLegalPrecedentFrom
chosen
Indicates that one legal case, decision, or argument relies on, cites, or is based upon the legal precedent established by another.
- 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_69f76df28d8c819089f2c5799fe7d079 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79533b88c8190934ec4cb21770e24 |
completed | May 3, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f79104f5b48190a496cdffde8472da |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.