Triple
T16415127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | K1A carbine |
E398663
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object | S&T Motiv |
E1209933
|
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: S&T Motiv | Statement: [K1A carbine, manufacturer, S&T Motiv]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: S&T Motiv Context triple: [K1A carbine, manufacturer, S&T Motiv]
-
A.
S&T Motiv
chosen
S&T Motiv is a South Korean defense company known for designing and producing small arms and other military weapons systems.
-
B.
Dinas Mot
Dinas Mot is a prominent rock formation in Snowdonia, Wales, renowned for its classic multi-pitch traditional climbing routes.
-
C.
MOTC
MOTC is the government ministry in Taiwan responsible for overseeing national transportation systems and communications infrastructure.
-
D.
Motok
The Motok are an indigenous ethnic community of Upper Assam in northeastern India, known for their distinct cultural traditions and historical presence in the region.
-
E.
Nomentum
Nomentum was an ancient town in Latium, northeast of Rome, known as a minor but historically significant settlement along important Roman roads.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e3287741008190856882b7f34024fc |
completed | April 18, 2026, 6:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c6a89988190a44515f1ca08099f |
completed | May 10, 2026, 8:06 a.m. |
Created at: April 10, 2026, 5:09 a.m.