Triple
T20863502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How to Murder Your Wife |
E513684
|
entity |
| Predicate | leadActress |
P6108
|
FINISHED |
| Object | Virna Lisi |
—
|
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: Virna Lisi | Statement: [How to Murder Your Wife, leadActress, Virna Lisi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Virna Lisi Context triple: [How to Murder Your Wife, leadActress, Virna Lisi]
-
A.
Virna Lisi
chosen
Virna Lisi was an acclaimed Italian actress known for her beauty, versatility, and award-winning performances in European and Hollywood films from the 1950s through the 1990s.
-
B.
Arlene Vrhel
Arlene Vrhel is an American restaurateur best known as the longtime wife of actor Joe Mantegna.
-
C.
Nita Naldi
Nita Naldi was a prominent American silent film actress best known for her sultry vamp roles opposite stars like Rudolph Valentino in the early 1920s.
-
D.
Irma Vuillier
Irma Vuillier was the wife of French sculptor Jules Dalou and a figure associated with his personal and artistic life in 19th-century France.
-
E.
Lili Sepe
Lili Sepe is an American actress best known for her role in the horror film "It Follows."
- 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c45d2ec4819098abbb901b9fcd87 |
completed | April 21, 2026, 12:27 a.m. |
Created at: April 16, 2026, 12:44 p.m.