Triple
T21955778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Top Banana |
E542182
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Rose Marie |
—
|
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: Rose Marie | Statement: [Top Banana, starring, Rose Marie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rose Marie Context triple: [Top Banana, starring, Rose Marie]
-
A.
Rose Marie
"Rose Marie" is a popular country and yodeling song best known as one of Slim Whitman’s signature hits.
-
B.
Rose Marie
chosen
Rose Marie was an American actress and comedian best known for her role as wisecracking comedy writer Sally Rogers on the classic television sitcom The Dick Van Dyke Show.
-
C.
Myrna Dell
Myrna Dell was an American film and television actress known for her roles in 1940s and 1950s Hollywood productions, particularly in film noir and B-movies.
-
D.
Myrna Adele Williams
Myrna Adele Williams, better known as Myrna Loy, was a celebrated American film actress renowned for her sophisticated wit and iconic role as Nora Charles in "The Thin Man" series.
-
E.
Myrna Fahey
Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f124404f38819080bae736a52a51cd |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:59 p.m.