Triple
T22132304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean People's Navy |
E546933
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | KPN |
—
|
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: KPN | Statement: [Korean People's Navy, abbreviation, KPN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KPN Context triple: [Korean People's Navy, abbreviation, KPN]
-
A.
KPN
chosen
KPN is the abbreviation commonly used for the Korean People's Navy, the maritime branch of North Korea's armed forces.
-
B.
Kpn
Kpn is the official station code used to identify Kampen railway station in the Netherlands.
-
C.
Telenet Group
Telenet Group is a major Belgian telecommunications and entertainment provider offering services such as broadband internet, television, and mobile telephony.
-
D.
Cablecom
Cablecom was a major Swiss cable television and telecommunications provider that later became known as UPC Switzerland.
-
E.
Deutsche Telekom
Deutsche Telekom is a major German telecommunications company and one of the largest telecom providers in Europe, offering mobile, fixed-line, and internet services worldwide.
- 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1298746888190967b4e3ae0558e9e |
completed | April 28, 2026, 9:41 p.m. |
Created at: April 16, 2026, 8:32 p.m.