Triple
T1411759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Permanent Representatives' Committee |
E31819
|
entity |
| Predicate | chairChosenFrom |
P19512
|
FINISHED |
| Object | Ambassadors of AU member states |
—
|
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: Ambassadors of AU member states | Statement: [Permanent Representatives' Committee, chairChosenFrom, Ambassadors of AU member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chairChosenFrom Context triple: [Permanent Representatives' Committee, chairChosenFrom, Ambassadors of AU member states]
-
A.
chairSelectedFrom
chosen
Indicates that a particular chair has been chosen from a larger set or collection of chairs.
-
B.
chairType
Indicates the specific kind or category of chair that an entity is classified as.
-
C.
canChair
Indicates that an entity has the authority or capability to preside over, lead, or chair a meeting, committee, or similar group.
-
D.
coChairWith
Indicates that two or more entities share the role of chairing the same group, event, or organization jointly.
-
E.
otherSeat
Indicates that one entity is the alternative or different seat relative to another seat in a given context.
- 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_69a49919a994819086528951bc224775 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c3e1da988190bc7c187e193539b6 |
completed | March 1, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69a4bf048b648190ab77d9b45cb4855f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.