Triple
T5978944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AK-47 |
E133070
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object | Izhmash |
E399592
|
NE 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: Izhmash | Statement: [AK-47, manufacturer, Izhmash]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Izhmash Context triple: [AK-47, manufacturer, Izhmash]
-
A.
Katyusha rocket launcher
The Katyusha rocket launcher was a Soviet World War II-era multiple rocket artillery system famed for its devastating salvos and distinctive howling sound.
-
B.
Shaposhnikov
Shaposhnikov is a Russian surname most notably associated with Soviet military leader Boris Shaposhnikov.
-
C.
S-25 Berkut
The S-25 Berkut was an early Soviet fixed surface-to-air missile system developed in the 1950s to provide high-altitude air defense for Moscow during the Cold War.
-
D.
SU-100 self-propelled gun
The SU-100 self-propelled gun was a Soviet World War II tank destroyer armed with a powerful 100 mm gun and built on the chassis of the T-34 medium tank.
-
E.
Izhevsk Mechanical Plant
chosen
Izhevsk Mechanical Plant is a major Russian arms manufacturer known for producing a wide range of firearms and military equipment.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c0086f45e8819098f73dd16d45ec9d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04a3e686c81908910c0881ac1624d |
completed | March 22, 2026, 7:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0e41d23848190bc7835eb6313b6a5 |
completed | March 23, 2026, 6:56 a.m. |
Created at: March 22, 2026, 4:04 p.m.