Triple
T24075768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Code de la sécurité sociale |
E596353
|
entity |
| Predicate | aPourObjet |
P110638
|
FINISHED |
| Object | protection sociale des assurés |
—
|
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: protection sociale des assurés | Statement: [Code de la sécurité sociale, aPourObjet, protection sociale des assurés]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aPourObjet Context triple: [Code de la sécurité sociale, aPourObjet, protection sociale des assurés]
-
A.
objet
chosen
Indicates that one entity is the object (recipient or target) of an action or relation performed by another entity.
-
B.
appearsToPour
Indicates that one entity is visually perceived as pouring a substance or object into or onto another entity, regardless of whether the pouring actually occurs.
-
C.
notableObject
Indicates that an entity is especially significant, famous, or noteworthy as an object in a given context or domain.
-
D.
objectUsed
Indicates that one entity is used as a tool, instrument, or resource in performing an action involving another entity.
-
E.
appartientÀ
Indicates that one entity belongs to, is a member of, or is part of 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_69e288c3999c8190809b282a04813dec |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1db1dd874819087120b06b90be485 |
completed | April 29, 2026, 10:19 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:42 p.m.