Triple
T38380254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collège Stendhal de Fosses |
E893739
|
entity |
| Predicate | operatedInSchoolSystem |
P124658
|
FINISHED |
| Object | French public education system |
—
|
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: French public education system | Statement: [Collège Stendhal de Fosses, operatedInSchoolSystem, French public education system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedInSchoolSystem Context triple: [Collège Stendhal de Fosses, operatedInSchoolSystem, French public education system]
-
A.
operatesInSchoolSystem
Indicates that an entity carries out its functions or activities within a particular school system or educational district.
-
B.
operatedAsSchoolUntil
Indicates that an entity functioned in the role or capacity of a school up to a specified end time or date.
-
C.
typeOfSchoolOperated
Indicates the specific category or kind of school that an entity is responsible for operating.
-
D.
isInEducationalSystemOf
chosen
Indicates that one entity belongs to, is administered by, or operates within the educational system governed by another entity.
-
E.
operatesSchoolsFor
Indicates that one entity manages and runs schools on behalf of or for the benefit 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_69f76e4b1f748190a380696a16eae4a2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a036b0755888190a68a673664f0ea46 |
completed | May 12, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_6a036228676c8190aac9c90f7d8cedf7 |
completed | May 12, 2026, 5:23 p.m. |
Created at: May 3, 2026, 4:31 p.m.