Triple
T22628178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalashnikov rifle family |
E558478
|
entity |
| Predicate | globalProliferation |
P35548
|
FINISHED |
| Object | widely used worldwide |
—
|
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: widely used worldwide | Statement: [Kalashnikov rifle family, globalProliferation, widely used worldwide]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: globalProliferation Context triple: [Kalashnikov rifle family, globalProliferation, widely used worldwide]
-
A.
world
chosen
Indicates a relationship or context that spans or pertains to the entire world or global scope.
-
B.
globalStatus
Indicates the overall state or condition of an entity as evaluated at a system-wide or global level.
-
C.
geopoliticalScope
Indicates the geographic or political area within which an entity’s authority, relevance, or effect is defined or applies.
-
D.
internationalConcern
Indicates that an issue, event, or situation is regarded as significant or problematic by multiple countries or the international community as a whole.
-
E.
governmentWorld
Indicates that a government has authority over, administers, or is associated with a particular world or planetary domain.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e3ed1d48190a093013d829901b9 |
completed | April 29, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 3:02 p.m.