Triple
T8652577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sockeye salmon |
E205134
|
entity |
| Predicate | migratesFrom |
P36610
|
FINISHED |
| Object | ocean |
—
|
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: ocean | Statement: [Sockeye salmon, migratesFrom, ocean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: migratesFrom Context triple: [Sockeye salmon, migratesFrom, ocean]
-
A.
migrationFrom
chosen
Indicates that an entity has moved, originated, or been transferred away from a specified source location or context.
-
B.
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.
-
C.
migrationBackground
Indicates that an entity has a personal or familial history of moving from one country or region to another, typically across national borders.
-
D.
supportsMigrationOf
Indicates that one entity enables, facilitates, or is compatible with the migration or transfer of another entity from one environment, system, or context to another.
-
E.
migrationCompatibilityWith
Indicates that one entity can be transitioned, upgraded, or moved to another entity or environment without incompatibilities or conflicts.
- 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_69ca834e56848190abb0eeaec9dedd32 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc484051b48190b1d0cc63426c204d |
completed | March 31, 2026, 10:18 p.m. |
| PD | Predicate disambiguation | batch_69cc45619460819091e83ffdec99c865 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:29 p.m.