Triple
T34869372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susitna River delta |
E1005704
|
entity |
| Predicate | isCriticalHabitatFor |
P14557
|
FINISHED |
| Object | Cook Inlet beluga whale |
—
|
NE NERFINISHED |
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: Cook Inlet beluga whale | Statement: [Susitna River delta, isCriticalHabitatFor, Cook Inlet beluga whale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCriticalHabitatFor Context triple: [Susitna River delta, isCriticalHabitatFor, Cook Inlet beluga whale]
-
A.
isMajorHabitatFor
chosen
Indicates that one entity serves as a primary or significant natural living environment for another entity.
-
B.
designatedAsWildlifeRefuge
Indicates that an area has been officially assigned the status and protections of a wildlife refuge.
-
C.
isEcologicalRefugeWithin
Indicates that one ecological refuge is spatially contained within the boundaries of another specified area or refuge.
-
D.
hasConservationConcernIn
Indicates that an entity is subject to a specified conservation concern status within a particular geographic area or jurisdiction.
-
E.
stateOfConservation
Indicates the condition or preservation status of an entity, typically in terms of how intact, degraded, or at risk it is.
- 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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782f4f10081908f97f6d0d2dbeec7 |
completed | May 3, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69f780ff71cc8190a67e71076fbad81a |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.