Triple
T38690263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tervingi |
E949240
|
entity |
| Predicate | migratedBecauseOf |
P42539
|
FINISHED |
| Object | Hunnic pressure |
—
|
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: Hunnic pressure | Statement: [Tervingi, migratedBecauseOf, Hunnic pressure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: migratedBecauseOf Context triple: [Tervingi, migratedBecauseOf, Hunnic pressure]
-
A.
migratedAcross
Indicates movement of an entity from one side of a boundary, region, or area to the other, typically implying a significant relocation or crossing.
-
B.
migrationCause
chosen
Indicates the reason or driving factor that leads an entity to migrate from one place to another.
-
C.
hasReasonForMigration
Indicates that there exists a specific cause, motive, or justification for an entity’s act of migrating from one place to another.
-
D.
migrationFrom
Indicates that an entity has moved, originated, or been transferred away from a specified source location or context.
-
E.
replacedBecause
Indicates that one entity has been substituted for another specifically due to a particular reason or cause.
- 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_69f76efe16148190befd5dd59c3dfeaa |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcdfbc71c481908ba7f87907b17782 |
completed | May 7, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe580b8819087f143596b2c79c0 |
completed | May 7, 2026, 6:37 p.m. |
Created at: May 3, 2026, 4:33 p.m.