Triple
T23721847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China and North Korea |
E586165
|
entity |
| Predicate | ChinaRole |
P153701
|
FINISHED |
| Object | North Korea's main trading partner |
—
|
LITERAL 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: North Korea's main trading partner | Statement: [China and North Korea, ChinaRole, North Korea's main trading partner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ChinaRole Context triple: [China and North Korea, ChinaRole, North Korea's main trading partner]
-
A.
roleInChina
Indicates that one entity holds or performs a specific role, position, or function within the context of China.
-
B.
ChineseLeader
Indicates that the subject is a person who holds or has held a top political leadership position in China.
-
C.
ChineseObjective
Indicates that an entity has an objective, goal, or target specifically related to China or the Chinese context.
-
D.
ChinaPosition
Indicates the stance, policy, or viewpoint officially held or expressed by China regarding a particular issue, event, or entity.
-
E.
ChineseOperation
Indicates an operation or activity carried out by a Chinese entity or within a Chinese context.
- F. None of above. chosen
Provenance (4 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b91177c08190bea6e62ed13e2495 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
| PDg | Predicate description generation | batch_69f15b453da88190889a8d9b21727958 |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 17, 2026, 7:02 p.m.