Triple
T23172283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame Sousatzka |
E578890
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Bernice Rubens |
—
|
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: Bernice Rubens | Statement: [Madame Sousatzka, screenwriter, Bernice Rubens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bernice Rubens Context triple: [Madame Sousatzka, screenwriter, Bernice Rubens]
-
A.
Bernice Rubens
chosen
Bernice Rubens was a Welsh novelist and Booker Prize winner known for her psychologically rich and often darkly comic explorations of family, identity, and morality.
-
B.
Bernice Bourne
Bernice Bourne is an individual known primarily for being among the notable people interred at Flushing Cemetery in Queens, New York.
-
C.
Alma Rubens
Alma Rubens was an American silent film actress of the 1910s and 1920s, known for her dramatic roles and troubled personal life.
-
D.
Barbara Feldon
Barbara Feldon is an American actress and former model best known for her role as the stylish and intelligent Agent 99 on the 1960s television comedy series "Get Smart."
-
E.
Kathryn Erbe
Kathryn Erbe is an American actress best known for her role as Detective Alexandra Eames on the television series "Law & Order: Criminal Intent."
- 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_69e245fd2a388190b814c0dfa15f7148 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f30ce148190a6de928c8213399e |
completed | April 29, 2026, 4:55 a.m. |
Created at: April 17, 2026, 4:04 p.m.