Triple
T21634821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peggy Eaton affair |
E533928
|
entity |
| Predicate | hasParticipant |
P149
|
FINISHED |
| Object | John Branch |
—
|
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: John Branch | Statement: [Peggy Eaton affair, hasParticipant, John Branch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Branch Context triple: [Peggy Eaton affair, hasParticipant, John Branch]
-
A.
John Branch
John Branch is a Pulitzer Prize–winning American journalist known for his long-form narrative sports and adventure reporting for The New York Times.
-
B.
John Branch
chosen
John Branch was an early 19th-century American politician who served as Governor of North Carolina, a U.S. Senator, and Secretary of the Navy under President Andrew Jackson.
-
C.
John Brasfield
John Brasfield is the stepchild of American comedian and actor Jack Carter.
-
D.
Carlos Battey
Carlos Battey is a Grammy-winning American songwriter and record producer known for his work across pop and R&B with artists such as Justin Bieber and Madonna.
-
E.
William Ragsdale
William Ragsdale is an American actor best known for his lead role in the 1985 horror-comedy film "Fright Night" and its sequel.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef538c5fbc8190a3316cf91f9516dc |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:35 p.m.