Triple

T15904893
Position Surface form Disambiguated ID Type / Status
Subject Marcello Mastroianni E385685 entity
Predicate spouse P13 FINISHED
Object Flora Carabella
Flora Carabella was an Italian actress best known for her work in mid-20th-century Italian cinema and theatre.
E1183521 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: Flora Carabella | Statement: [Marcello Mastroianni, spouse, Flora Carabella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flora Carabella
Context triple: [Marcello Mastroianni, spouse, Flora Carabella]
  • A. Rosabella
    Rosabella is the shy, kind-hearted waitress who becomes the central romantic heroine in Frank Loesser’s Broadway musical "The Most Happy Fella."
  • B. Rosana
    Rosana is a municipality in the state of São Paulo, Brazil, known for hosting a campus of São Paulo State University (UNESP).
  • C. Rosana
    Rosana is a Brazilian professional footballer known for her successful international career and contributions to top women’s clubs, including Avaldsnes IL.
  • D. Viviana
    Viviana is a central protagonist in the television sitcom "Love, Inc.," around whom much of the show's matchmaking and personal drama revolves.
  • E. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • 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: Flora Carabella
Triple: [Marcello Mastroianni, spouse, Flora Carabella]
Generated description
Flora Carabella was an Italian actress best known for her work in mid-20th-century Italian cinema and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Flora Carabella
Target entity description: Flora Carabella was an Italian actress best known for her work in mid-20th-century Italian cinema and theatre.
  • A. Rosabella
    Rosabella is the shy, kind-hearted waitress who becomes the central romantic heroine in Frank Loesser’s Broadway musical "The Most Happy Fella."
  • B. Rosana
    Rosana is a municipality in the state of São Paulo, Brazil, known for hosting a campus of São Paulo State University (UNESP).
  • C. Rosana
    Rosana is a Brazilian professional footballer known for her successful international career and contributions to top women’s clubs, including Avaldsnes IL.
  • D. Viviana
    Viviana is a central protagonist in the television sitcom "Love, Inc.," around whom much of the show's matchmaking and personal drama revolves.
  • E. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565956588190ba4726a2879b677d completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb051a05081908c349cd9a1ff247a completed May 9, 2026, 10:08 p.m.
NEDg Description generation batch_69ffb1742e2c8190ab7fd714a8f38312 completed May 9, 2026, 10:13 p.m.
NED2 Entity disambiguation (via description) batch_69ffb1eedaf481908d70e3517fbd5492 completed May 9, 2026, 10:15 p.m.
Created at: April 10, 2026, 4:52 a.m.