Triple
T22628131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalashnikov rifle family |
E558478
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | AKM |
—
|
NE NERFINISHED |
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: AKM | Statement: [Kalashnikov rifle family, hasPart, AKM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AKM Context triple: [Kalashnikov rifle family, hasPart, AKM]
-
A.
AKM
chosen
The AKM is a modernized, widely produced variant of the AK-47 assault rifle, known for its reliability, simplicity, and extensive use in militaries and conflicts around the world.
-
B.
AKOM
AKOM is a South Korean animation studio known for providing outsourced animation work on numerous popular Western television series, including many episodes of the original Transformers cartoon.
-
C.
AMKC
AMKC is a large jail facility on Rikers Island in New York City, named after former Correction Commissioner Anna M. Kross.
-
D.
AKRM
AKRM is a Mauritian institution dedicated to the promotion, standardization, and development of the Mauritian Creole language.
-
E.
AKJ
AKJ is the ICAO airline designator assigned to Akasa Air, a low-cost carrier based in India.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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. |
Created at: April 17, 2026, 3:02 p.m.