Triple
T21035660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beulah Marie Dix |
E518182
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Beulah Marie Dix |
—
|
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: Beulah Marie Dix | Statement: [Beulah Marie Dix, name, Beulah Marie Dix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beulah Marie Dix Context triple: [Beulah Marie Dix, name, Beulah Marie Dix]
-
A.
Beulah Marie Dix
chosen
Beulah Marie Dix was an American playwright, novelist, and screenwriter active in the early 20th century, known for her historical dramas and contributions to silent and early sound films.
-
B.
Beulah Edmondson
Beulah Edmondson was the wife of influential Tammany Hall political boss Richard Croker.
-
C.
Beulah Elizabeth Richardson
Beulah Elizabeth Richardson, better known as Beah Richards, was an American actress, poet, and civil rights activist acclaimed for her powerful performances on stage and screen.
-
D.
Mabel Ray Willis
Mabel Ray Willis is the daughter of American actor Bruce Willis and model Emma Heming Willis.
-
E.
Beulah Brown
Beulah Brown is the central housekeeper character from the mid-20th-century American radio and television comedy series "Beulah."
- 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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc858d808190a8489aac801a4f51 |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 2:02 p.m.