Triple
T21421851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conseil privé |
E528455
|
entity |
| Predicate | fonctionPrincipale |
P18495
|
FINISHED |
| Object | affaires judiciaires |
—
|
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: affaires judiciaires | Statement: [Conseil privé, fonctionPrincipale, affaires judiciaires]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fonctionPrincipale Context triple: [Conseil privé, fonctionPrincipale, affaires judiciaires]
-
A.
mainFunctions
chosen
Indicates that the subject serves as the primary or central functional component or role for the object.
-
B.
publicFunction
Indicates that a function or method is accessible from outside its defining scope, module, or class (i.e., it has public visibility).
-
C.
functie
Indicates that one entity serves as a function, role, or operational purpose in relation to another entity.
-
D.
typicalFunction
Indicates that something serves as the usual or characteristic function or role of an entity.
-
E.
exercisesFunction
Indicates that one entity performs or carries out the function, role, or capability associated with another entity.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b2d17f5081908f0185011eae3160 |
completed | April 22, 2026, 11:36 a.m. |
| PD | Predicate disambiguation | batch_69e61633f8208190a2a849457c4e4198 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:48 p.m.