Triple
T19701763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean officials |
E473114
|
entity |
| Predicate | ideology |
P496
|
FINISHED |
| Object | Songun |
—
|
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: Songun | Statement: [North Korean officials, ideology, Songun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Songun Context triple: [North Korean officials, ideology, Songun]
-
A.
Songun
chosen
Songun is North Korea’s military-first political ideology that prioritizes the Korean People’s Army as the central force of the state and society.
-
B.
Haidamaky
Haidamaky is a historical poem by Ukrainian writer Taras Shevchenko that depicts the 18th-century Haidamak uprisings against Polish rule.
-
C.
Rakkasans
Rakkasans is the distinctive nickname of the 3rd Brigade Combat Team of the U.S. Army’s 101st Airborne Division, renowned for its airborne and air assault operations.
-
D.
Gwangandaegyo
Gwangandaegyo is a prominent suspension bridge in Busan, South Korea, known for its scenic coastal views and nighttime LED light displays.
-
E.
Aegukga
Aegukga is the national anthem of South Korea, expressing patriotic devotion and love for the country.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b667908190841bb5fb7bfdb3f7 |
completed | April 20, 2026, 3:13 p.m. |
Created at: April 10, 2026, 1:46 p.m.