Triple
T18259771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blanche Yurka |
E437317
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Blanche Yurka |
—
|
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: Blanche Yurka | Statement: [Blanche Yurka, name, Blanche Yurka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blanche Yurka Context triple: [Blanche Yurka, name, Blanche Yurka]
-
A.
Blanche Yurka
chosen
Blanche Yurka was an American actress and opera singer best known for her powerful character roles on stage and in early Hollywood films.
-
B.
Blanche Denicola
Blanche Denicola is known primarily for being married to American actor Harry Guardino.
-
C.
Blanche Rubin
Blanche Rubin is the wife of American screenwriter and filmmaker Bruce Joel Rubin, known for his work on films such as "Ghost" and "Jacob's Ladder."
-
D.
Blanche Cruppi
Blanche Cruppi was a French woman known primarily as the daughter of prominent politician and lawyer Jean Cruppi.
-
E.
Blanche Hanalis
Blanche Hanalis was an American television writer and producer best known for adapting and developing popular family-oriented series and literary works for TV.
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4fd89899c8190b8b652c4f61aa5cf |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 10:34 a.m.