Triple
T23425697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arby’s |
E560789
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Leroy Raffel |
—
|
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: Leroy Raffel | Statement: [Arby’s, foundedBy, Leroy Raffel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leroy Raffel Context triple: [Arby’s, foundedBy, Leroy Raffel]
-
A.
John Vinal
John Vinal was an early settler and prominent local figure after whom the town of Vinalhaven, Maine, was named.
-
B.
Forrest Raffel
chosen
Forrest Raffel was an American entrepreneur best known as the co-founder of the fast-food restaurant chain Arby’s.
-
C.
Douglas Garman
Douglas Garman was a British literary figure and editor associated with left-wing politics and the son of art patron and collector Walter Garman.
-
D.
Stephen Fleischman
Stephen Fleischman is an American documentary filmmaker and television producer best known for his work at PBS and for being married to acclaimed film editor Dede Allen.
-
E.
Philip Bruns
Philip Bruns was an American character actor best known for his television and film roles in the 1970s and 1980s, including his work on the satirical soap opera "Mary Hartman, Mary Hartman."
- 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_69e2454cb1108190ab21ada5411a7146 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a54951688190a3c5382971af3e41 |
completed | April 29, 2026, 6:29 a.m. |
Created at: April 17, 2026, 5:47 p.m.