Triple
T26971958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia's 6th congressional district |
E679340
|
entity |
| Predicate | 2017SpecialElectionWinner |
P98311
|
FINISHED |
| Object | Karen Handel |
—
|
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: Karen Handel | Statement: [Georgia's 6th congressional district, 2017SpecialElectionWinner, Karen Handel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 2017SpecialElectionWinner Context triple: [Georgia's 6th congressional district, 2017SpecialElectionWinner, Karen Handel]
-
A.
electionResult2017
chosen
Indicates the outcome or status of an election that took place in the year 2017.
-
B.
AdamsDivisionWinner
Indicates that the entity has won the Adams Division championship in a given season or competition.
-
C.
stateDelegatesWonBy
Indicates the number of delegates a candidate or party has secured from a particular state in an election or nominating contest.
-
D.
afterElectionSenator
Indicates that one person holds the position of senator following a specified election.
-
E.
representativeOfState
Indicates that an entity serves as an official representative or agent acting on behalf of a particular state or government.
- 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_69eeeb507a7081909d516e1fa08b7d29 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f62125bd7081909c1901e3bf566669 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:40 a.m.