Triple
T8207406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Awful Truth |
E191720
|
entity |
| Predicate | BestSupportingActorNominee |
P40640
|
FINISHED |
| Object | Ralph Bellamy |
E117112
|
NE FINISHED |
How this triple was built (3 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: Ralph Bellamy | Statement: [The Awful Truth, BestSupportingActorNominee, Ralph Bellamy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ralph Bellamy Context triple: [The Awful Truth, BestSupportingActorNominee, Ralph Bellamy]
-
A.
Ralph Bellamy
chosen
Ralph Bellamy was an American actor known for his prolific film, television, and stage career, including notable roles in classic screwball comedies and the film "Rosemary's Baby."
-
B.
Richard Kiley
Richard Kiley was an American stage and screen actor best known for his Tony Award–winning performance as Don Quixote in the original Broadway production of "Man of La Mancha."
-
C.
E. G. Marshall
E. G. Marshall was an American character actor known for his authoritative, dignified roles in film, television, and theater, including prominent performances in works like "12 Angry Men" and various acclaimed TV dramas.
-
D.
William Claude Rains
William Claude Rains was a distinguished British-American character actor renowned for his roles in classic films such as "The Invisible Man," "Casablanca," and "Mr. Smith Goes to Washington."
-
E.
Ralph Nelson
Ralph Nelson was an American film and television director, producer, and writer known for works such as "Lilies of the Field" and "Requiem for a Heavyweight."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BestSupportingActorNominee Context triple: [The Awful Truth, BestSupportingActorNominee, Ralph Bellamy]
-
A.
bestSupportingActorWinner
Indicates that an entity has received the award for Best Supporting Actor for a particular work or event.
-
B.
bestSupportingActorWinningFilm
Indicates that a film is the one for which an actor won the Best Supporting Actor award.
-
C.
bestSupportingActressWinner
Indicates that the subject is the person who won the Best Supporting Actress award for the specified work, year, or event.
-
D.
bestSupportingActorFilm
Indicates the film for which a person received the Best Supporting Actor award.
-
E.
supportingActorNominee
chosen
Indicates that an entity has been nominated for an award recognizing their performance in a supporting acting role.
- F. None of above.
Provenance (4 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_69ca82c7f3e08190857bf1fc63b2a10c |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb726b520081908ce4a03bd14dfcdf |
completed | March 31, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc69b9b8c819082a164433312166e |
completed | April 2, 2026, 1:30 a.m. |
| PD | Predicate disambiguation | batch_69cb36ad01ac81909609b15f6a6c8581 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:43 p.m.