Triple
T36759615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Armed Forces for the Liberation of Angola |
E908156
|
entity |
| Predicate | disarmedAfter |
P186268
|
FINISHED |
| Object | death of Jonas Savimbi |
—
|
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: death of Jonas Savimbi | Statement: [Armed Forces for the Liberation of Angola, disarmedAfter, death of Jonas Savimbi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disarmedAfter Context triple: [Armed Forces for the Liberation of Angola, disarmedAfter, death of Jonas Savimbi]
-
A.
disarmamentBy
Indicates the action or process of removing or reducing weapons or military capabilities carried out by a specified agent.
-
B.
disassembledAfter
Indicates that one entity was taken apart or broken down into its components at a point in time later than another specified event or state.
-
C.
unarmed
Indicates that an entity is not carrying or equipped with any weapons.
-
D.
removedArmament
Indicates that an entity has taken away or stripped another entity of its weapons or armaments.
-
E.
disarmamentMethod
Indicates the specific means, process, or technique by which disarmament is carried out.
- F. None of above. chosen
Provenance (4 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_69f76e779bec8190be0e1f87a131e0f4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7cabacc1481909e839454ce1057f7 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
| PDg | Predicate description generation | batch_69f7c9f4c7c48190ba918d8d5dc8dfd9 |
completed | May 3, 2026, 10:19 p.m. |
Created at: May 3, 2026, 4:12 p.m.