Triple
T19944232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean economy |
E479380
|
entity |
| Predicate | foreignInvestmentLevel |
P137947
|
FINISHED |
| Object | very low |
—
|
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: very low | Statement: [North Korean economy, foreignInvestmentLevel, very low]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foreignInvestmentLevel Context triple: [North Korean economy, foreignInvestmentLevel, very low]
-
A.
accessMechanismForForeignInvestors
Indicates the method or channel through which foreign investors are allowed to access or participate in a given market, asset, or investment opportunity.
-
B.
economicIntegrationLevel
Indicates the degree to which two or more entities’ economies are interconnected and coordinated through shared markets, policies, or institutions.
-
C.
investmentGeography
Indicates the geographic region or location where an investment is targeted, managed, or primarily focused.
-
D.
foreignInfluence
Indicates that one entity exerts influence, control, or significant impact on another entity from a different country or external origin.
-
E.
investmentScope
Indicates the range or boundaries of activities, assets, or sectors that an investment is intended or allowed to cover.
- 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a64b2788190a49c4ed40aa93b98 |
completed | April 20, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69e537f47c508190853c4e009c6b5566 |
completed | April 19, 2026, 8:15 p.m. |
| PDg | Predicate description generation | batch_69e543c42c688190a22f4d31ec692377 |
completed | April 19, 2026, 9:06 p.m. |
Created at: April 10, 2026, 1:54 p.m.