Triple
T31712962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regional Special Forces (Ethiopia) |
E809376
|
entity |
| Predicate | reformAnnouncedIn |
P50931
|
FINISHED |
| Object | April 2023 |
—
|
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: April 2023 | Statement: [Regional Special Forces (Ethiopia), reformAnnouncedIn, April 2023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reformAnnouncedIn Context triple: [Regional Special Forces (Ethiopia), reformAnnouncedIn, April 2023]
-
A.
reformAnnouncedBy
Indicates that a reform or change has been officially declared or made public by a particular entity.
-
B.
timeOfMajorReforms
chosen
Indicates the specific time period during which significant reforms or major changes took place.
-
C.
advocatedReformOf
Indicates that one entity publicly supported or promoted changes to another entity, typically aiming to improve or modify its structure, policies, or practices.
-
D.
replacedInReform
Indicates that one entity was substituted or superseded by another as part of a formal reform or restructuring process.
-
E.
lastReform
Indicates the most recent reform or change that was applied to an entity, typically linking the entity to its latest reform event or version.
- 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:16 p.m.