Triple
T32353078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sri Lankan New Zealander |
E826657
|
entity |
| Predicate | migrationReasonMayInclude |
P134391
|
FINISHED |
| Object | education |
—
|
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: education | Statement: [Sri Lankan New Zealander, migrationReasonMayInclude, education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: migrationReasonMayInclude Context triple: [Sri Lankan New Zealander, migrationReasonMayInclude, education]
-
A.
migrationCause
Indicates the reason or driving factor that leads an entity to migrate from one place to another.
-
B.
hasReasonForMigration
chosen
Indicates that there exists a specific cause, motive, or justification for an entity’s act of migrating from one place to another.
-
C.
migrationPolicy
Indicates the rules or strategies governing how entities move, transfer, or transition from one context, location, or state to another.
-
D.
reasonForRelocation
Indicates the underlying cause, motivation, or circumstance that led an entity to move from one location to another.
-
E.
migrationBackground
Indicates that an entity has a personal or familial history of moving from one country or region to another, typically across national borders.
- 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_69f34915a2588190bb3178f5ec2f48f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be5b27408190ab72ab435a4279de |
completed | May 3, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:49 a.m.