Triple
T10002042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afghan Local Police |
E197349
|
entity |
| Predicate | authorizedToCarryWeapons |
P50881
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Afghan Local Police, authorizedToCarryWeapons, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorizedToCarryWeapons Context triple: [Afghan Local Police, authorizedToCarryWeapons, yes]
-
A.
prohibitedWeaponType
Indicates that a particular type of weapon is classified as not allowed or forbidden under specified rules, laws, or agreements.
-
B.
entitlesToArms
chosen
Indicates that one party has a right or legal claim to possess or bear weapons or armaments in relation to another party or context.
-
C.
hasMilitaryAuthority
Indicates that one entity possesses formal power or command to direct, control, or make decisions over the military activities or forces of another entity.
-
D.
canBeHeldByActiveDutyOfficer
Indicates that the specified role, position, or responsibility is eligible to be occupied or performed by an officer who is currently serving on active duty.
-
E.
limitedWeaponType
Indicates that the use or availability of a weapon is restricted to a specific type or set of types.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc9078788190a4e75dd7ff830c63 |
completed | April 2, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69cd1da2cf9081908a6c0eb5247d0bc2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:51 p.m.