Triple
T18787518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iron Triangle (Korean War) |
E459415
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Chorwon |
—
|
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: Chorwon | Statement: [Iron Triangle (Korean War), contains, Chorwon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chorwon Context triple: [Iron Triangle (Korean War), contains, Chorwon]
-
A.
Cheorwon
chosen
Cheorwon is a county in South Korea’s Gangwon Province, known for its location along the heavily fortified Demilitarized Zone and its significant Korean War battlefields.
-
B.
Colhoon
Colhoon is a surname variant associated with the Scottish Clan Colquhoun.
-
C.
Chonhar
Chonhar is a small settlement in southern Ukraine located near the Chongar Peninsula, close to the administrative boundary with Crimea.
-
D.
Gachsaran
Gachsaran is a city in southwestern Iran known for its significant oil and gas fields and role in the country’s energy industry.
-
E.
Chon
Chon is a former Navy SEAL and one of the two marijuana-growing protagonists in Oliver Stone’s crime thriller film "Savages."
- 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e597828cb481908fe569747f816e15 |
completed | April 20, 2026, 3:03 a.m. |
Created at: April 10, 2026, 11:52 a.m.