Triple
T22085639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Singing Vagabond |
E545763
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Frank Ellis |
—
|
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: Frank Ellis | Statement: [The Singing Vagabond, castMember, Frank Ellis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Ellis Context triple: [The Singing Vagabond, castMember, Frank Ellis]
-
A.
Frank Ellis
chosen
Frank Ellis is an actor known for his role in the film "Crashing Towers."
-
B.
Robert Ellis
Robert Ellis is an American music executive and producer best known for managing major artists including Diana Ross.
-
C.
Frank Elliott
Frank Elliott was the husband of Australian-born silent film actress Dorothy Cumming, known for her roles in early Hollywood cinema.
-
D.
Peter B. Ellis
Peter B. Ellis is a film editor known for his work on animated features, including the 2019 adaptation of The Addams Family.
-
E.
Robert Fitch
Robert Fitch is a relatively common personal name shared by multiple individuals, including figures in fields such as politics, academia, and the arts.
- 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128ba24ac819082fc4aa274553481 |
completed | April 28, 2026, 9:38 p.m. |
Created at: April 16, 2026, 8:29 p.m.