Triple

T19315593
Position Surface form Disambiguated ID Type / Status
Subject Serena Calabi Modigliani E483088 entity
Predicate familyName P18 FINISHED
Object Calabi
Calabi is an Italian surname associated with individuals such as Serena Calabi Modigliani.
 E619745 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: Calabi | Statement: [Serena Calabi Modigliani, familyName, Calabi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Calabi
Context triple: [Serena Calabi Modigliani, familyName, Calabi]
  • A. Kähler
    Kähler is a German surname most notably associated with Erich Kähler, a mathematician known for his foundational work in differential geometry and complex manifolds.
  • B. Trevisani
    Trevisani are the inhabitants or natives of the Italian city of Treviso, typically associated with its local culture and traditions.
  • C. Beltrami
    Beltrami is an Italian surname borne by various notable individuals across fields such as music, mathematics, and the arts.
  • D. Morbidelli
    Morbidelli was an Italian motorcycle manufacturer and racing team known for its success in Grand Prix motorcycle racing, particularly in the 1970s.
  • E. Kalmus
    Kalmus is a surname most notably associated with Herbert Kalmus, the co-founder of the pioneering color motion picture company Technicolor.
  • 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: Calabi
Triple: [Serena Calabi Modigliani, familyName, Calabi]
Generated description
Calabi is an Italian surname associated with individuals such as Serena Calabi Modigliani.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Calabi
Target entity description: Calabi is an Italian surname associated with individuals such as Serena Calabi Modigliani.
  • A. Kähler
    Kähler is a German surname most notably associated with Erich Kähler, a mathematician known for his foundational work in differential geometry and complex manifolds.
  • B. Trevisani
    Trevisani are the inhabitants or natives of the Italian city of Treviso, typically associated with its local culture and traditions.
  • C. Beltrami chosen
    Beltrami is an Italian surname borne by various notable individuals across fields such as music, mathematics, and the arts.
  • D. Morbidelli
    Morbidelli was an Italian motorcycle manufacturer and racing team known for its success in Grand Prix motorcycle racing, particularly in the 1970s.
  • E. Kalmus
    Kalmus is a surname most notably associated with Herbert Kalmus, the co-founder of the pioneering color motion picture company Technicolor.
  • F. None of above.

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_69d8e8d04d5c8190baa816986f2b1d1e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e60d833034819092a8414d5e0fc26e completed April 20, 2026, 11:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a071461923081909deb4c114cab2560 completed May 15, 2026, 12:41 p.m.
NEDg Description generation batch_6a0714eb6a0c8190bec7ae8ef785a4ab completed May 15, 2026, 12:43 p.m.
NED2 Entity disambiguation (via description) batch_6a0718ee8adc8190a74685f9783ba5d5 completed May 15, 2026, 1 p.m.
Created at: April 10, 2026, 1:32 p.m.