Triple
T20986551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John H. Winder |
E516904
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | John Henry Winder |
—
|
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 Henry Winder | Statement: [John H. Winder, fullName, John Henry Winder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Henry Winder Context triple: [John H. Winder, fullName, John Henry Winder]
-
A.
John H. Winder
chosen
John H. Winder was a Confederate brigadier general during the American Civil War, best known for overseeing prisoner-of-war camps including the notorious Andersonville prison.
-
B.
Frank H. Wheeler
Frank H. Wheeler was an American industrialist and early automotive pioneer who co-founded and helped finance the Indianapolis Motor Speedway.
-
C.
Frederick H. Winston
Frederick H. Winston was a 19th-century American lawyer and politician best known as the founding partner of the international law firm Winston & Strawn.
-
D.
Winslow Fegley
Winslow Fegley is an American child actor known for roles in family and fantasy films such as "Timmy Failure: Mistakes Were Made" and "Nightbooks."
-
E.
William Wheeler
William Wheeler is an American screenwriter known for his work on films such as the biographical drama "Queen of Katwe."
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbe31cec8190a1007414148b8abe |
completed | April 21, 2026, 4:24 a.m. |
Created at: April 16, 2026, 1:49 p.m.