Triple
T18958567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deana Martin |
E463848
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Betty McDonald |
—
|
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: Betty McDonald | Statement: [Deana Martin, mother, Betty McDonald]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Betty McDonald Context triple: [Deana Martin, mother, Betty McDonald]
-
A.
Betty McDonald
chosen
Betty McDonald is the mother of Claudia Martin, the daughter of legendary entertainer Dean Martin.
-
B.
Betty McGlown
Betty McGlown was an original member of the vocal group that would later become the legendary Motown act The Supremes.
-
C.
Betty Hicks
Betty Hicks was the wife of famed American tenor and film star Mario Lanza, known for supporting him throughout his celebrated but turbulent career.
-
D.
Betty Brown
Betty Brown was the wife of American vaudeville performer and comedian Ted Healy, best known for his work with the early Three Stooges.
-
E.
Betty Sizemore
Betty Sizemore is the naive yet determined small-town waitress who becomes delusionally convinced she is a nurse in the dark comedy film "Nurse Betty."
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5d057a48190b82b5788b3281e28 |
completed | April 20, 2026, 7:29 a.m. |
Created at: April 10, 2026, noon