Triple
T22712359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breda-SAFAT machine gun |
E561634
|
entity |
| Predicate | rateOfFireRange |
P17731
|
FINISHED |
| Object | 700–900 rounds per minute |
—
|
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: 700–900 rounds per minute | Statement: [Breda-SAFAT machine gun, rateOfFireRange, 700–900 rounds per minute]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rateOfFireRange Context triple: [Breda-SAFAT machine gun, rateOfFireRange, 700–900 rounds per minute]
-
A.
rateOfFire
chosen
Indicates the frequency at which a weapon or system can discharge projectiles or shots over a given period of time.
-
B.
gunRate
Indicates the rate or frequency at which guns are present, owned, used, or involved in incidents within a given context.
-
C.
rangeStandardAmmunition
Indicates that the relationship specifies the standard type of ammunition used for a given range or weapon system.
-
D.
numberOfShotsFired
Indicates the total count of shots that were discharged in the described event or action.
-
E.
fireModes
Indicates the different ways or settings in which a weapon or device can be fired or operated.
- 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790998fc8190962e21a28dd08d29 |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:18 p.m.