Triple
T17357470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States (during Soviet–Afghan War) |
E421975
|
entity |
| Predicate | providedWeaponType |
P6014
|
FINISHED |
| Object | small arms |
—
|
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: small arms | Statement: [United States (during Soviet–Afghan War), providedWeaponType, small arms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providedWeaponType Context triple: [United States (during Soviet–Afghan War), providedWeaponType, small arms]
-
A.
hasWeaponType
chosen
Indicates that an entity is associated with or equipped with a specific type or category of weapon.
-
B.
typicalWeapon
Indicates that the object is a weapon commonly or characteristically used by the subject.
-
C.
weaponTypeTested
Indicates that a specific type of weapon has been subjected to a test or evaluation in the described context.
-
D.
supportsWeapon
Indicates that one entity is capable of accommodating, using, or being compatible with a specified weapon.
-
E.
relatedToWeaponType
Indicates that an entity has an association or connection with a specific type or category of weapon.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4976788190b00c00f710be6c46 |
completed | April 19, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69e3b02662d08190a07d0fb5c04b6f33 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.