Triple
T25355680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Union |
E635812
|
entity |
| Predicate | worksThroughMemberState |
P81251
|
FINISHED |
| Object | Zambia |
—
|
NE NERFINISHED |
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: Zambia | Statement: [African Union, worksThroughMemberState, Zambia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksThroughMemberState Context triple: [African Union, worksThroughMemberState, Zambia]
-
A.
hasMemberState
Indicates that an entity includes or comprises another entity as one of its constituent member states within a larger organizational or political structure.
-
B.
memberStatesAreMemberOf
Indicates that certain states belong to or hold membership in a particular organization, group, or union.
-
C.
memberStateSide1
Indicates that an entity participates as the first member state (or party) on one side of a bilateral or multilateral relationship or agreement.
-
D.
cooperatesWithStateIn
Indicates that an entity works jointly with a state or government body in pursuing shared goals, activities, or operations.
-
E.
throughMember
chosen
Indicates that a relationship or action occurs by means of, or is mediated or facilitated by, a particular member of a group or organization.
- 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_69e75a9ac5d881909387ed766e20cd47 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f6135293908190809e255bf6334760 |
completed | May 2, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69f611a72780819082f44e66ca2c6ac9 |
completed | May 2, 2026, 3 p.m. |
Created at: April 21, 2026, 1:35 p.m.