Triple
T4009960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OECD Directorate for Education and Skills |
E90617
|
entity |
| Predicate | officeHeldByHead |
P45587
|
FINISHED |
| Object | Director for Education and Skills |
—
|
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: Director for Education and Skills | Statement: [OECD Directorate for Education and Skills, officeHeldByHead, Director for Education and Skills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHeldByHead Context triple: [OECD Directorate for Education and Skills, officeHeldByHead, Director for Education and Skills]
-
A.
officeHeldOf
chosen
Indicates that a specific office or position is (or was) held by a particular person or entity.
-
B.
officeHeldByMember
Indicates that a specific office or position is held or occupied by a particular member.
-
C.
officeHeldUnder
Indicates that one entity holds or has held an official position, role, or office under the authority, jurisdiction, or administration of another entity.
-
D.
officeHeldDuring
Indicates that a person occupied a specific official position during a particular time period.
-
E.
officeHeldByDecisionMaker
Indicates that a particular official position or office is occupied by the decision maker involved in a given decision or action.
- 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_69aed95e44088190aff7d90a151b1b20 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefaec08dc8190a341809059554f84 |
completed | March 9, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69aef8fa6fec81909b1190ecbba61410 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:34 p.m.