Triple
T15586052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Paul Island |
E374623
|
entity |
| Predicate | hasSpeciesColony |
P76008
|
FINISHED |
| Object | northern fur seal |
—
|
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: northern fur seal | Statement: [Saint Paul Island, hasSpeciesColony, northern fur seal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpeciesColony Context triple: [Saint Paul Island, hasSpeciesColony, northern fur seal]
-
A.
hostsColonyOf
chosen
Indicates that one entity serves as the living site or environment in which a colony of another entity resides or is established.
-
B.
colonyOf
Indicates that one entity is a colony belonging to, founded by, or politically dependent on another entity.
-
C.
colonyType
Indicates the specific classification or kind of colony associated with an entity (e.g., its organizational or structural type).
-
D.
colonyInteractedWith
Indicates that a colony has engaged in some form of interaction or exchange with another entity.
-
E.
belongsToSpecies
Indicates that an individual organism is a member of, or classified under, a particular biological species.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e4900408190aadb48b001db4169 |
completed | April 16, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69deda817e9881909b0c66fc9056f7d5 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:11 a.m.