Triple
T21089877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonny Perdue |
E519607
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sonny Perdue |
—
|
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: Sonny Perdue | Statement: [Sonny Perdue, name, Sonny Perdue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonny Perdue Context triple: [Sonny Perdue, name, Sonny Perdue]
-
A.
Sonny Perdue
chosen
Sonny Perdue is an American politician and former Governor of Georgia who served as the U.S. Secretary of Agriculture under President Donald Trump.
-
B.
Mark Hawley
Mark Hawley is a British sound engineer and record producer best known for his long-term collaboration with and marriage to musician Tori Amos.
-
C.
Michele Hicks
Michele Hicks is an American actress and former fashion model known for her roles in television series such as "The Shield" and various independent films.
-
D.
Michael D. Lumpkin
Michael D. Lumpkin is a former U.S. Navy SEAL officer who served as Assistant Secretary of Defense for Special Operations and Low-Intensity Conflict.
-
E.
Tim Suby
Tim Suby is a music producer known for his work on tracks such as "Jaguar."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b507dd9081908fb8bfcbef4c8b46 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7094dd65481909391ed74115afc23 |
completed | April 21, 2026, 5:21 a.m. |
Created at: April 16, 2026, 2:50 p.m.