Triple
T28329177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republican Party presidential primaries, 2020 |
E717490
|
entity |
| Predicate | somePrimariesCancelledBy |
P44890
|
FINISHED |
| Object | state Republican parties |
—
|
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: state Republican parties | Statement: [Republican Party presidential primaries, 2020, somePrimariesCancelledBy, state Republican parties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: somePrimariesCancelledBy Context triple: [Republican Party presidential primaries, 2020, somePrimariesCancelledBy, state Republican parties]
-
A.
wasInitiallyCancelled
Indicates that an event, action, or request was first cancelled at some point, regardless of its later status.
-
B.
canceledBy
chosen
Indicates that an action, event, or agreement was annulled or called off by a specific entity.
-
C.
canceledAfter
Indicates that one event or action was canceled at a point in time occurring after another specified event or action.
-
D.
canceledBefore
Indicates that one event, reservation, or commitment was canceled at a time earlier than another specified event or reference point.
-
E.
programCancelledInFavorOf
Indicates that one program was cancelled so that another program could take its place or be prioritized instead.
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f649322d1881909297d1b1c607937d |
completed | May 2, 2026, 6:57 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 12:30 a.m.