Triple
T25171728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loi sur la gestion des finances publiques |
E630338
|
entity |
| Predicate | titreAbrégé |
P38
|
FINISHED |
| Object | Loi sur la gestion des finances publiques |
—
|
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: Loi sur la gestion des finances publiques | Statement: [Loi sur la gestion des finances publiques, titreAbrégé, Loi sur la gestion des finances publiques]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titreAbrégé Context triple: [Loi sur la gestion des finances publiques, titreAbrégé, Loi sur la gestion des finances publiques]
-
A.
title
chosen
Indicates that one entity serves as the formal name or designation of another entity.
-
B.
titles
Indicates that one entity holds a formal title, designation, or name associated with another entity.
-
C.
titlePhrase
Indicates that one entity is a phrase functioning as the title or name of another entity.
-
D.
titleDescription
Indicates that one entity serves as a descriptive or explanatory subtitle or summary associated with the title of another entity.
-
E.
titleThrough
Indicates a relationship where one entity holds or is identified by a specific title by means of, or via the mediation of, another entity or context.
- 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_69e75a87c9b88190ab60731902a99750 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46d47886c81908507ce1d55e5643c |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:20 p.m.