Triple
T27920003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Brogan |
E706177
|
entity |
| Predicate | electedOnTicketWith |
P4036
|
FINISHED |
| Object | Jeb Bush |
—
|
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: Jeb Bush | Statement: [Frank Brogan, electedOnTicketWith, Jeb Bush]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electedOnTicketWith Context triple: [Frank Brogan, electedOnTicketWith, Jeb Bush]
-
A.
electedWith
chosen
Indicates that one entity attained an elected position or office together with, or as part of the same electoral outcome as, another entity.
-
B.
heldOnSameBallotAs
Indicates that two elections, contests, or measures were presented to voters on the same ballot in the same electoral event.
-
C.
isElectedFor
Indicates that an entity attains a position, role, or office as the result of an election for that specific position.
-
D.
electedWithin
Indicates that one entity was chosen or appointed to a position, office, or role within the jurisdiction, boundaries, or organizational scope of another entity.
-
E.
wasElectoralVehicleFor
Indicates that one entity served as the primary means, platform, or instrument through which another entity pursued electoral participation or gained electoral power.
- 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_69ef96b6cc808190aab19fb18b235f4b |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 27, 2026, 6:56 p.m.