Triple
T36595046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southeastern Angola |
E902773
|
entity |
| Predicate | sawMilitaryPresenceOf |
P14275
|
FINISHED |
| Object | South African Defence Force |
—
|
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: South African Defence Force | Statement: [Southeastern Angola, sawMilitaryPresenceOf, South African Defence Force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sawMilitaryPresenceOf Context triple: [Southeastern Angola, sawMilitaryPresenceOf, South African Defence Force]
-
A.
hasMilitaryPresence
chosen
Indicates that a military force is present in, stationed at, or operating within a particular location or entity.
-
B.
civilianPresence
Indicates the presence or involvement of non-combatant individuals in a given location, situation, or event.
-
C.
viewsMilitaryAs
Indicates that one entity holds a particular perception, attitude, or evaluative stance toward the military as an institution or concept.
-
D.
militaryActivity
Indicates that an entity is engaged in, associated with, or affected by actions, operations, or preparations conducted by armed forces.
-
E.
hasMilitarySecurity
Indicates that an entity provides, maintains, or is responsible for military protection or defense for another entity or area.
- 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_69f76e6592e88190bac4eb00a46e9df9 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.