Triple
T18707887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patricia Roc |
E457420
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Patricia Roc |
—
|
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: Patricia Roc | Statement: [Patricia Roc, name, Patricia Roc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patricia Roc Context triple: [Patricia Roc, name, Patricia Roc]
-
A.
Patricia Roc
chosen
Patricia Roc was a popular British film actress of the 1940s, best known for her roles in melodramas and wartime dramas produced by major UK studios.
-
B.
Karin Ferrer
Karin Ferrer is known as the wife of Sean Hepburn Ferrer, the son of actress Audrey Hepburn and actor Mel Ferrer.
-
C.
Maria Conchita Alonso
Maria Conchita Alonso is a Cuban-Venezuelan actress and singer known for her work in both Latin American and Hollywood films and television.
-
D.
Patricia Farina
Patricia Farina is best known as the wife of the late American actor and former Chicago police officer Dennis Farina.
-
E.
Carla Quevedo
Carla Quevedo is an Argentine actress known for her work in both Latin American and U.S. film and television, including roles in acclaimed dramas and crime series.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e567185c648190848ca47498eb56b3 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 10, 2026, 11:50 a.m.