Triple
T10139767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaeltacht of Cloich Cheann Fhaola |
E226949
|
entity |
| Predicate | educationMedium |
P12427
|
FINISHED |
| Object | Irish-language education |
—
|
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: Irish-language education | Statement: [Gaeltacht of Cloich Cheann Fhaola, educationMedium, Irish-language education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: educationMedium Context triple: [Gaeltacht of Cloich Cheann Fhaola, educationMedium, Irish-language education]
-
A.
mediumOfInstruction
chosen
Indicates that a particular language or medium is used as the primary means of instruction or teaching in an educational context.
-
B.
educates
Indicates that one entity provides instruction, knowledge, or training to another entity.
-
C.
educationRight
Indicates that an entity holds a right or entitlement to receive education or educational opportunities.
-
D.
educatedIn
Indicates that an entity received education or formal training at a specified institution or place.
-
E.
educationTrend
Indicates a pattern or direction of change over time in some aspect of education, such as participation, attainment, or performance.
- 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_69ca8433ec308190b8b25a6fe359c34c |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cde8851844819092330e74561b7e34 |
completed | April 2, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba4f5d88190ba68e63be10b08c7 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:06 p.m.