Triple
T28490535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Defence Force |
E720950
|
entity |
| Predicate | usedWeaponVariantOf |
P706
|
FINISHED |
| Object | R1 rifle – variant of FN FAL |
—
|
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: R1 rifle – variant of FN FAL | Statement: [South African Defence Force, usedWeaponVariantOf, R1 rifle – variant of FN FAL]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedWeaponVariantOf Context triple: [South African Defence Force, usedWeaponVariantOf, R1 rifle – variant of FN FAL]
-
A.
usedWeapon
chosen
Indicates that an entity employed a specific weapon as the means or tool to carry out an action or event.
-
B.
formerWeapon
Indicates that an entity once functioned as a weapon but no longer serves in that role.
-
C.
weaponUsedIn
Indicates that a particular weapon is employed or involved in carrying out a specific event or action.
-
D.
weaponInherited
Indicates that a weapon has been passed down or transferred from one entity to another as an inheritance.
-
E.
armedVariants
Indicates that one entity is a version or model of another that is equipped with weapons or enhanced armaments.
- 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_69f01a5a47148190b0a7e111bc432e0a |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6645ba71c81908044ade6ab577018 |
completed | May 2, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:01 a.m.