Triple
T22581454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Accattone |
E544577
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Mario Cipriani
Mario Cipriani was an Italian actor known for his role in Pier Paolo Pasolini’s 1961 film "Accattone."
|
E1544234
|
NE FINISHED |
How this triple was built (4 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: Mario Cipriani | Statement: [Accattone, castMember, Mario Cipriani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mario Cipriani Context triple: [Accattone, castMember, Mario Cipriani]
-
A.
Tonye Patano
Tonye Patano is an American actress best known for her role as Heylia James on the television series "Weeds."
-
B.
Gino Torretta
Gino Torretta is a former American football quarterback best known for his standout college career at the University of Miami, where he led dominant Hurricanes teams in the early 1990s.
-
C.
Vito Volpe
Vito Volpe is an individual notable enough to be recognized as a prominent bearer of the surname Volpe.
-
D.
Vince Papale
Vince Papale is a former Philadelphia Eagles walk-on wide receiver whose unlikely rise from bartender and teacher to the NFL inspired the film "Invincible."
-
E.
Nick Aliotti
Nick Aliotti is an American football coach best known for his long tenure as the University of Oregon’s defensive coordinator, where he helped build some of the nation’s top collegiate defenses.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mario Cipriani Triple: [Accattone, castMember, Mario Cipriani]
Generated description
Mario Cipriani was an Italian actor known for his role in Pier Paolo Pasolini’s 1961 film "Accattone."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mario Cipriani Target entity description: Mario Cipriani was an Italian actor known for his role in Pier Paolo Pasolini’s 1961 film "Accattone."
-
A.
Tonye Patano
Tonye Patano is an American actress best known for her role as Heylia James on the television series "Weeds."
-
B.
Gino Torretta
Gino Torretta is a former American football quarterback best known for his standout college career at the University of Miami, where he led dominant Hurricanes teams in the early 1990s.
-
C.
Vito Volpe
Vito Volpe is an individual notable enough to be recognized as a prominent bearer of the surname Volpe.
-
D.
Vince Papale
Vince Papale is a former Philadelphia Eagles walk-on wide receiver whose unlikely rise from bartender and teacher to the NFL inspired the film "Invincible."
-
E.
Nick Aliotti
Nick Aliotti is an American football coach best known for his long tenure as the University of Oregon’s defensive coordinator, where he helped build some of the nation’s top collegiate defenses.
- F. None of above. chosen
Provenance (5 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b3d5460cc819082b4924809b1ae56 |
completed | May 18, 2026, 4:24 p.m. |
| NEDg | Description generation | batch_6a0b3e659bbc81908ebe404365577ddf |
completed | May 18, 2026, 4:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b3f401fb08190b59206d6e5edbaf7 |
completed | May 18, 2026, 4:33 p.m. |
Created at: April 16, 2026, 8:53 p.m.