Triple
T1020705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freedom Flights |
E22032
|
entity |
| Predicate | typeOfMigration |
P11725
|
FINISHED |
| Object | forced migration |
—
|
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: forced migration | Statement: [Freedom Flights, typeOfMigration, forced migration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfMigration Context triple: [Freedom Flights, typeOfMigration, forced migration]
-
A.
associatedWithMigrationType
Indicates that one entity has a specified connection or linkage to a particular type or category of migration.
-
B.
migration
Indicates the movement of entities from one location or context to another, often across boundaries or over time.
-
C.
historicalMigrationType
chosen
Indicates the type or category of migration that occurred in a historical context between entities.
-
D.
typeOfOperation
Indicates the specific kind or category of operation being performed or referenced in a given context.
-
E.
migrationEvent
Indicates an event in which one or more entities move or relocate from one place or context to another, typically across defined boundaries or regions.
- 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_69a493d6e380819097b384986ffc315c |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7dd76b081909ed4d2f7adb6480d |
completed | March 1, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69a4b724c7908190a5b92a57fbdbff4e |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.