Triple
T9072326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skeena River estuary |
E217397
|
entity |
| Predicate | supportsLifeStage |
P2036
|
FINISHED |
| Object | juvenile salmon rearing |
—
|
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: juvenile salmon rearing | Statement: [Skeena River estuary, supportsLifeStage, juvenile salmon rearing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsLifeStage Context triple: [Skeena River estuary, supportsLifeStage, juvenile salmon rearing]
-
A.
supportsLife
chosen
Indicates that one entity provides conditions or resources that allow another entity to live, grow, or remain biologically viable.
-
B.
lifeStage
Indicates the specific phase or period in an entity’s development or lifecycle that it is currently in.
-
C.
supportsLifestyle
Indicates that one entity provides the resources, conditions, or assistance necessary for another entity to maintain a particular way of living.
-
D.
followsCharacterInLifeStage
Indicates that one entity chronologically succeeds or comes after another entity within a specific stage or period of life.
-
E.
exploresLifeStage
Indicates that one entity investigates, examines, or studies a particular stage in the life or development of another entity.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc955ffa04819086be5763133c5067 |
completed | April 1, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69cc65f881248190bfd220bb28a9fb5f |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:12 p.m.