Triple
T22100543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phenomena |
E546157
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Franco Fraticelli |
—
|
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: Franco Fraticelli | Statement: [Phenomena, editedBy, Franco Fraticelli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Franco Fraticelli Context triple: [Phenomena, editedBy, Franco Fraticelli]
-
A.
Franco Fraticelli
chosen
Franco Fraticelli was an Italian film editor best known for his long-standing collaboration with director Dario Argento on numerous influential horror and giallo films.
-
B.
Michele Farinola
Michele Farinola is a film producer known for her work on the acclaimed music documentary "Linda Ronstadt: The Sound of My Voice."
-
C.
Ettore Fagiuoli
Ettore Fagiuoli was an Italian architect known for his early 20th-century stadium and civic building designs.
-
D.
Francesco Satolli
Francesco Satolli was an Italian cardinal and theologian who became the first Apostolic Delegate to the United States and a prominent advisor on Catholic education and doctrine in the late 19th century.
-
E.
Filippo Nigro
Filippo Nigro is an Italian actor known for his work in contemporary Italian cinema and television, often appearing in crime dramas and socially themed films.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291501508190ad5689be5abb2ba6 |
completed | April 28, 2026, 9:39 p.m. |
Created at: April 16, 2026, 8:30 p.m.