Triple
T22159270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hobson's Choice |
E547624
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Brenda de Banzie |
—
|
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: Brenda de Banzie | Statement: [Hobson's Choice, leadActor, Brenda de Banzie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brenda de Banzie Context triple: [Hobson's Choice, leadActor, Brenda de Banzie]
-
A.
Brenda de Banzie
chosen
Brenda de Banzie was a British stage and film actress known for her strong character roles in mid-20th-century cinema and theatre.
-
B.
Brenda Grate
Brenda Grate is an American voice actress best known for voicing Faline in Disney’s animated film "Bambi."
-
C.
Karla Crome
Karla Crome is a British actress and writer known for her roles in television series such as Misfits, Under the Dome, and Carnival Row.
-
D.
Jennifer Batten
Jennifer Batten is an American rock and fusion guitarist best known for her virtuosic playing and high-profile work with Michael Jackson and Jeff Beck.
-
E.
Brenda Bethune
Brenda Bethune is an American politician and businesswoman who serves as the mayor of Myrtle Beach, South Carolina.
- 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_69e11e3c4c5c81908d336165816b12e0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a2b5b10819090630fbadacb67af |
completed | April 28, 2026, 9:44 p.m. |
Created at: April 16, 2026, 8:33 p.m.