Triple
T21428125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Stallworth |
E528614
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ron Stallworth |
—
|
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: Ron Stallworth | Statement: [Ron Stallworth, name, Ron Stallworth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ron Stallworth Context triple: [Ron Stallworth, name, Ron Stallworth]
-
A.
Ron Stallworth
chosen
Ron Stallworth is a real-life African-American police officer best known for infiltrating the Ku Klux Klan in the 1970s, an undercover operation later depicted in the film "BlacKkKlansman."
-
B.
Jack Epps Jr.
Jack Epps Jr. is an American screenwriter best known for co-writing the blockbuster action film "Top Gun."
-
C.
Officer Powell
Officer Powell is a fictional police officer character portrayed by actor Rob Morgan.
-
D.
FBI Agent Albert Rosenfield
FBI Agent Albert Rosenfield is a sharp-tongued, brilliant forensic specialist in the television series "Twin Peaks," known for his acerbic wit and uncompromising professionalism.
-
E.
Lester Crawford
Lester Crawford was the husband of American stage and film actress Helen Broderick.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b3e74bcc81909ad66e3c59152ffc |
completed | April 22, 2026, 11:41 a.m. |
Created at: April 16, 2026, 5:49 p.m.