Triple
T12392858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pacific salmon |
E296040
|
entity |
| Predicate | migrateTo |
P93048
|
FINISHED |
| Object | freshwater spawning grounds |
—
|
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: freshwater spawning grounds | Statement: [Pacific salmon, migrateTo, freshwater spawning grounds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: migrateTo Context triple: [Pacific salmon, migrateTo, freshwater spawning grounds]
-
A.
migrationFrom
Indicates that an entity has moved, originated, or been transferred away from a specified source location or context.
-
B.
migratesBetween
Indicates movement of an entity from one location or region to another, typically in a recurring or seasonal pattern.
-
C.
migration
Indicates the movement of entities from one location or context to another, often across boundaries or over time.
-
D.
migrationBackground
Indicates that an entity has a personal or familial history of moving from one country or region to another, typically across national borders.
-
E.
laterMigrationsTo
Indicates that one migration event or movement of entities occurred after another in time.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69dbaecf13748190ae40c7b95164f914 |
completed | April 12, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69dbadfddefc81909ef7fde23b181b5c |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 8, 2026, 9:54 p.m.