Triple
T25253968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Union passport |
E633116
|
entity |
| Predicate | movementTypePromoted |
P96692
|
FINISHED |
| Object | free movement of persons |
—
|
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: free movement of persons | Statement: [African Union passport, movementTypePromoted, free movement of persons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementTypePromoted Context triple: [African Union passport, movementTypePromoted, free movement of persons]
-
A.
movementCharacteristicPromoted
chosen
Indicates that an entity encourages, supports, or enhances a particular way, style, or quality of movement.
-
B.
promotedToRankBy
Indicates that an entity was elevated to a particular rank or position through the action or decision of another entity.
-
C.
promotedFrom
Indicates that an entity has advanced to a new position, role, or status from a specified prior one.
-
D.
promotedToGeneral
Indicates that an individual has been elevated in rank to the position or title of general.
-
E.
hasBeenPromotedBy
Indicates that one entity has received a promotion as a result of the decision or action taken by another entity.
- 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_69e75a922ad481908f4f1f884583cb42 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4808e7b288190ad7444ccbef04d80 |
completed | May 1, 2026, 10:29 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 1:12 p.m.