Triple
T13660480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French universities |
E326980
|
entity |
| Predicate | typicalAcademicYearStart |
P111033
|
FINISHED |
| Object | September or October |
—
|
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: September or October | Statement: [French universities, typicalAcademicYearStart, September or October]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAcademicYearStart Context triple: [French universities, typicalAcademicYearStart, September or October]
-
A.
academicYearType
Indicates the classification of an academic year according to its structural or administrative type (e.g., semester-based, quarter-based, fiscal year, etc.).
-
B.
schoolYear
Indicates the academic year or grade level in which an entity (typically a student or class) is situated within an educational system.
-
C.
timeWithinAcademicYear
Indicates that a specified time or date falls within the bounds of a defined academic year period.
-
D.
matriculationYear
Indicates the calendar year in which an individual formally enrolled or was admitted into an educational program or institution.
-
E.
hasSchoolYearEndMonth
Indicates the month in which a school year ends for a given educational institution or system.
- F. None of above. chosen
Provenance (4 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_69d8076d8270819092afc2f0e9c359a8 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc620df208190afaccf3ddd10aa60 |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe8a027081908d8f884b89707a5e |
completed | April 12, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69dbc59ca1a88190a6abd3bd00554c93 |
completed | April 12, 2026, 4:17 p.m. |
Created at: April 9, 2026, 9:52 p.m.