Triple
T21509851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China–North Korea relations |
E530686
|
entity |
| Predicate | chinaShareOfNorthKoreaTrade |
P63200
|
FINISHED |
| Object | >70% in many years |
—
|
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: >70% in many years | Statement: [China–North Korea relations, chinaShareOfNorthKoreaTrade, >70% in many years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chinaShareOfNorthKoreaTrade Context triple: [China–North Korea relations, chinaShareOfNorthKoreaTrade, >70% in many years]
-
A.
countryTradeShare
chosen
Indicates the proportion of a country’s total trade that is conducted with a specific partner or in a specific category.
-
B.
percentageOfWorldTrade
Indicates the proportion of total global trade that is accounted for by a particular entity or group.
-
C.
controlledTradeWith
Indicates a regulated or restricted trading relationship in which one entity manages, oversees, or limits the trade activities conducted with another entity.
-
D.
hasRegionalTrade
Indicates that there is an ongoing or established trade relationship between two regions or territorial entities.
-
E.
isLinkedEconomicallyTo
Indicates that two entities are connected through economic relationships such as trade, investment, financial flows, or shared market dependencies.
- F. None of above.
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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea84dfbc8190a23d9a7d6eb2c2b5 |
completed | April 23, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:25 p.m.