Triple

T18073295
Position Surface form Disambiguated ID Type / Status
Subject Prince of Foxes E432486 entity
Predicate starredActor P5563 FINISHED
Object Marina Berti
Marina Berti was an Italian film and television actress known for her supporting roles in numerous historical and costume dramas from the 1940s through the 1970s.
E1303696 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: Marina Berti | Statement: [Prince of Foxes, starredActor, Marina Berti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marina Berti
Context triple: [Prince of Foxes, starredActor, Marina Berti]
  • A. Marisa Borini
    Marisa Borini is an Italian concert pianist and actress, best known as the mother of singer-songwriter and former French First Lady Carla Bruni.
  • B. Federica De Cola
    Federica De Cola is an Italian actress known for her roles in contemporary Italian cinema and television.
  • C. Simona Altobelli
    Simona Altobelli is an individual notable enough to be recognized as a prominent bearer of the Altobelli surname.
  • D. Silvia de Bondini
    Silvia de Bondini was the wife of influential French political economist and European integration pioneer Jean Monnet.
  • E. Alessandra Celi
    Alessandra Celi is the daughter of Italian actor and director Adolfo Celi, known for his work in European cinema and the James Bond film "Thunderball."
  • 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: Marina Berti
Triple: [Prince of Foxes, starredActor, Marina Berti]
Generated description
Marina Berti was an Italian film and television actress known for her supporting roles in numerous historical and costume dramas from the 1940s through the 1970s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marina Berti
Target entity description: Marina Berti was an Italian film and television actress known for her supporting roles in numerous historical and costume dramas from the 1940s through the 1970s.
  • A. Marisa Borini
    Marisa Borini is an Italian concert pianist and actress, best known as the mother of singer-songwriter and former French First Lady Carla Bruni.
  • B. Federica De Cola
    Federica De Cola is an Italian actress known for her roles in contemporary Italian cinema and television.
  • C. Simona Altobelli
    Simona Altobelli is an individual notable enough to be recognized as a prominent bearer of the Altobelli surname.
  • D. Silvia de Bondini
    Silvia de Bondini was the wife of influential French political economist and European integration pioneer Jean Monnet.
  • E. Alessandra Celi
    Alessandra Celi is the daughter of Italian actor and director Adolfo Celi, known for his work in European cinema and the James Bond film "Thunderball."
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ccefcdc4819086d0b224731bfc4d completed April 19, 2026, 12:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03567685fc8190a63da27de99a1101 completed May 12, 2026, 4:33 p.m.
NEDg Description generation batch_6a0357dd52dc8190990b5dc2fe1b4720 completed May 12, 2026, 4:39 p.m.
NED2 Entity disambiguation (via description) batch_6a03585051d4819085e4ea76b0a8ea8b completed May 12, 2026, 4:41 p.m.
Created at: April 10, 2026, 10:26 a.m.