Triple
T25378424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SAATM |
E633113
|
entity |
| Predicate | aimsToRemove |
P74638
|
FINISHED |
| Object | market access restrictions among African 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: market access restrictions among African states | Statement: [SAATM, aimsToRemove, market access restrictions among African states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimsToRemove Context triple: [SAATM, aimsToRemove, market access restrictions among African states]
-
A.
aimsToEliminate
chosen
Indicates an intention or directed effort by one entity to remove, destroy, or completely get rid of another entity or condition.
-
B.
claimsToEliminate
Indicates that one entity asserts it will remove, eradicate, or put an end to another entity or condition.
-
C.
requestToRemoveAt
Indicates a request has been made for something to be removed at a specific time or location.
-
D.
laterRemovedTo
Indicates that an entity was moved or transferred to a location or state at a later time, after an earlier condition or placement.
-
E.
mayRemove
Indicates that one entity is permitted or authorized to remove another entity or its association.
- 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_69e75a90c0dc819092f928b6ea0ecc72 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f55e5d7e2c8190937af482e50e6cad |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:38 p.m.