Triple
T31048501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulster Scots language |
E791191
|
entity |
| Predicate | hasEducationalSupportIn |
P175695
|
FINISHED |
| Object | Northern Ireland schools |
—
|
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: Northern Ireland schools | Statement: [Ulster Scots language, hasEducationalSupportIn, Northern Ireland schools]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEducationalSupportIn Context triple: [Ulster Scots language, hasEducationalSupportIn, Northern Ireland schools]
-
A.
hasEducationalSupportFrom
Indicates that one entity receives educational assistance, guidance, or resources from another entity.
-
B.
hasEducationalStatus
Indicates that an entity possesses a particular level, state, or condition of formal education or academic attainment.
-
C.
hasEducationFund
Indicates that an entity possesses or is associated with a dedicated fund intended to support educational expenses or activities.
-
D.
hasEducationServices
Indicates that one entity provides or offers educational services to another entity or within a particular context.
-
E.
hasEducationIn
Indicates that an entity has received education, training, or formal study in a specified field, subject, or discipline.
- 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_69f224ca2fa881908a3ac5fedf207b90 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26ceb08819091c71c001e954936 |
completed | May 3, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69f6d6a482fc8190b526291cd99b8696 |
completed | May 3, 2026, 5:01 a.m. |
Created at: April 29, 2026, 9 p.m.