Triple
T19530237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Chinese |
E488635
|
entity |
| Predicate | historicalMigrationCause |
P90645
|
FINISHED |
| Object | poverty in Korea |
—
|
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: poverty in Korea | Statement: [Korean Chinese, historicalMigrationCause, poverty in Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalMigrationCause Context triple: [Korean Chinese, historicalMigrationCause, poverty in Korea]
-
A.
historicalPopulationMovement
Indicates the movement or migration of a population from one place to another during a specific historical period or event.
-
B.
historicalMigrationType
Indicates the type or category of migration that occurred in a historical context between entities.
-
C.
historicalReason
Indicates that one entity exists, occurs, or is justified because of causes, events, or circumstances rooted in the past of another entity.
-
D.
historicalMigrationFactor
chosen
Indicates that the relationship or condition is influenced by patterns, causes, or consequences of past human migration.
-
E.
majorImmigrationWaveFrom
Indicates that a significant, large-scale movement of immigrants originated from one place and arrived in another.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363ec6cc8190b9e9ac0196b288f9 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.