Triple
T31283505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | parquets généraux près les cours d’appel |
E797737
|
entity |
| Predicate | niveauDeJuridiction |
P152114
|
FINISHED |
| Object | deuxième degré |
—
|
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: deuxième degré | Statement: [parquets généraux près les cours d’appel, niveauDeJuridiction, deuxième degré]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: niveauDeJuridiction Context triple: [parquets généraux près les cours d’appel, niveauDeJuridiction, deuxième degré]
-
A.
jurisdictionLevel
Indicates the scope or tier of authority under which an entity or action is legally governed or regulated.
-
B.
judicialBranchLevel
chosen
Indicates the hierarchical level or tier within the judicial branch at which a given judicial body, office, or action operates.
-
C.
hadCourtLevel
Indicates the specific hierarchical level of the court at which a legal case or judicial action took place.
-
D.
typeOfJurisdiction
Indicates the specific kind or category of legal authority or control that one jurisdiction holds in relation to a given legal or administrative context.
-
E.
typeOfTribunal
Indicates the specific category or kind of tribunal (e.g., court or adjudicative body) to which an entity belongs.
- 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_69f224def9088190a37034eab3daf57f |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:13 p.m.