Triple
T22581453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Accattone |
E544577
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Adriana Asti |
—
|
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: Adriana Asti | Statement: [Accattone, castMember, Adriana Asti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adriana Asti Context triple: [Accattone, castMember, Adriana Asti]
-
A.
Adriana Asti
chosen
Adriana Asti is an Italian actress known for her work in European art-house cinema and collaborations with prominent directors such as Luchino Visconti and Bernardo Bertolucci.
-
B.
Adriana Novelli
Adriana Novelli is an editor known for her work on the film "Two Women."
-
C.
Adriana Pennino
Adriana Pennino is a fictional character from the "Rocky" film series, best known as Rocky Balboa’s shy yet supportive wife.
-
D.
Adriana Varela
Adriana Varela is an acclaimed Argentine tango singer known for her intense, smoky vocal style and modern interpretations of classic tangos.
-
E.
Fabiana Udenio
Fabiana Udenio is an Italian-Argentinian actress best known for her comedic and character roles in film and television, including a memorable turn in the Austin Powers franchise.
- 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_69e11e30d05481909df915354c89f0d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f15ff13e288190b5e4b527470be75e |
completed | April 29, 2026, 1:33 a.m. |
Created at: April 16, 2026, 8:53 p.m.