Triple
T27489473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WWAMI regional program |
E693839
|
entity |
| Predicate | partnerState |
P68813
|
FINISHED |
| Object | Washington |
—
|
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: Washington | Statement: [WWAMI regional program, partnerState, Washington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partnerState Context triple: [WWAMI regional program, partnerState, Washington]
-
A.
statePartner
chosen
Indicates that two entities are formally partnered or allied at the level of state or governmental institutions.
-
B.
partnerNation
Indicates that one entity is recognized as a collaborating or allied nation in relation to another entity.
-
C.
partnerContext
Indicates a contextual or situational relationship in which one entity is associated with or acts as a partner to another within a specific setting or framework.
-
D.
associatedState
Indicates that one entity is linked or connected to a particular state, condition, or status of another entity.
-
E.
partnerAffiliation
Indicates that two entities are formally associated as partners within an organization, project, or collaborative relationship.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 1:04 p.m.