Triple
T7317451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eugene Talmadge |
E168448
|
entity |
| Predicate | electedForOffice |
P1239
|
FINISHED |
| Object | Governor of Georgia in 1946 |
—
|
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: Governor of Georgia in 1946 | Statement: [Eugene Talmadge, electedForOffice, Governor of Georgia in 1946]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electedForOffice Context triple: [Eugene Talmadge, electedForOffice, Governor of Georgia in 1946]
-
A.
nominatedForOffice
Indicates that an entity has been formally put forward as a candidate to hold a particular office or position.
-
B.
electedOffice
chosen
Indicates that an entity holds or has held a particular office or position as a result of an election.
-
C.
electionForOffice
Indicates that an election event is held to select or fill a specific office or position.
-
D.
isUsuallyElectedFor
Indicates that an entity typically attains a position, role, or office through an election process.
-
E.
eligibleForOffice
Indicates that an entity meets the necessary requirements or qualifications to hold a particular office or position.
- 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_69c68a5251508190ad68df4151cfeb04 |
completed | March 27, 2026, 1:46 p.m. |
| NER | Named-entity recognition | batch_69c6ef178b3081908cd0c62466069741 |
completed | March 27, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69c6e7705f4881909793071dee50c557 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:02 p.m.