Triple
T19998710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MythBusters |
E494262
|
entity |
| Predicate | narrator |
P2181
|
FINISHED |
| Object | Robert Lee |
—
|
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: Robert Lee | Statement: [MythBusters, narrator, Robert Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Lee Context triple: [MythBusters, narrator, Robert Lee]
-
A.
Robert Lee
chosen
Robert Lee is a narrator and voice actor best known for providing the distinctive voiceover for the science entertainment television series MythBusters.
-
B.
Robert N. Lee
Robert N. Lee was an American screenwriter best known for his work on early Hollywood crime and gangster films.
-
C.
Robert E. Lee
Robert E. Lee was a prominent 19th-century American military officer best known as the leading Confederate general during the American Civil War.
-
D.
Robert E. Lee
Robert E. Lee is an American writer and television producer best known for co-creating the classic sitcom "The Honeymooners."
-
E.
Guy Levis Grant
Guy Levis Grant was an American dentist and educator best known as one of the ten founders of the historically Black fraternity Kappa Alpha Psi.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a09bdc819083305b08a11c6e34 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:32 p.m.