Triple
T7785054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kettle Creek |
E187220
|
entity |
| Predicate | commander |
P1061
|
FINISHED |
| Object | John Dooly |
E568698
|
NE 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: John Dooly | Statement: [Battle of Kettle Creek, commander, John Dooly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Dooly Context triple: [Battle of Kettle Creek, commander, John Dooly]
-
A.
John Dooly
chosen
John Dooly was an American Revolutionary War officer and Georgia patriot after whom Dooly County, Georgia, is named.
-
B.
Tom Muldoon
Tom Muldoon is a film editor known for his work on major Hollywood productions, including the action blockbuster "Transformers: Revenge of the Fallen."
-
C.
George Meehan
George Meehan was a cinematographer best known for helping establish the American Society of Cinematographers, a leading professional organization for film camerawork.
-
D.
John Briley
John Briley was an American screenwriter best known for his Academy Award-winning work on the film "Gandhi" and other politically charged dramas.
-
E.
Delmar O’Donnell
Delmar O’Donnell is a naive but good-hearted escaped convict and one of the three central companions in the Coen brothers’ film "O Brother, Where Art Thou?".
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cadf22d9b4819081b877c751204a22 |
completed | March 30, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb139059a08190a8a4df25ee09756b |
completed | March 31, 2026, 12:21 a.m. |
Created at: March 30, 2026, 4:23 p.m.