Triple
T10225466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stealing Beauty |
E243192
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Franco Arcalli |
E385019
|
NE FINISHED |
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 Arcalli | Statement: [Stealing Beauty, screenwriter, Franco Arcalli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Franco Arcalli Context triple: [Stealing Beauty, screenwriter, Franco Arcalli]
-
A.
Franco Arcalli
chosen
Franco Arcalli was an Italian film editor and screenwriter known for his innovative work on influential European art films of the 1960s and 1970s.
-
B.
Guido Quaroni
Guido Quaroni is an Italian-born Pixar technical director and voice actor best known for voicing the character Guido in the animated film "Cars."
-
C.
Carlo Rainaldi
Carlo Rainaldi was a prominent 17th-century Italian Baroque architect known for designing several major churches and urban monuments in Rome.
-
D.
Paolo Ajroldi
Paolo Ajroldi is an advertising executive best known for co-founding the global marketing and communications agency TBWA Worldwide.
-
E.
Giulio Berruti
Giulio Berruti is an Italian actor and former fashion model known for his roles in romantic comedies and drama films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d1f9cf6c81909a6b9e9b9d0a79fe |
completed | April 7, 2026, 9:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63449892881909d361815cbfcdee5 |
completed | May 2, 2026, 5:28 p.m. |
Created at: April 6, 2026, 11:17 a.m.