Triple

T13796557
Position Surface form Disambiguated ID Type / Status
Subject Keoma E331531 entity
Predicate screenwriter P2831 FINISHED
Object Nico Ducci
Nico Ducci is a screenwriter best known for his work on the Italian Western film "Keoma."
E1062999 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: Nico Ducci | Statement: [Keoma, screenwriter, Nico Ducci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nico Ducci
Context triple: [Keoma, screenwriter, Nico Ducci]
  • A. Nico Toscani
    Nico Toscani is a tough, maverick Chicago cop and former CIA operative portrayed by Steven Seagal in the action film "Above the Law."
  • B. Fabio Pittorru
    Fabio Pittorru was an Italian screenwriter and novelist known for his work on giallo and crime films in the 1960s and 1970s.
  • C. Dionys Mascolo
    Dionys Mascolo was a French writer, editor, and political intellectual known for his involvement in leftist movements and his long relationship with author Marguerite Duras.
  • D. Alessandro Benassi
    Alessandro Benassi is an Italian songwriter and music producer known for co-writing the hit song "Counting Stars."
  • E. Leonardo Antonelli
    Leonardo Antonelli was an Italian cardinal of the Roman Catholic Church who served as Dean of the College of Cardinals around the turn of the 19th century.
  • 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: Nico Ducci
Triple: [Keoma, screenwriter, Nico Ducci]
Generated description
Nico Ducci is a screenwriter best known for his work on the Italian Western film "Keoma."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nico Ducci
Target entity description: Nico Ducci is a screenwriter best known for his work on the Italian Western film "Keoma."
  • A. Nico Toscani
    Nico Toscani is a tough, maverick Chicago cop and former CIA operative portrayed by Steven Seagal in the action film "Above the Law."
  • B. Fabio Pittorru
    Fabio Pittorru was an Italian screenwriter and novelist known for his work on giallo and crime films in the 1960s and 1970s.
  • C. Dionys Mascolo
    Dionys Mascolo was a French writer, editor, and political intellectual known for his involvement in leftist movements and his long relationship with author Marguerite Duras.
  • D. Alessandro Benassi
    Alessandro Benassi is an Italian songwriter and music producer known for co-writing the hit song "Counting Stars."
  • E. Leonardo Antonelli
    Leonardo Antonelli was an Italian cardinal of the Roman Catholic Church who served as Dean of the College of Cardinals around the turn of the 19th century.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de025be1f08190aac525d72d7dc0c3 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b08508688190b7e8c33e6b65e25d completed May 3, 2026, 8:31 p.m.
NEDg Description generation batch_69f7b48bf704819098bfb70def28a0d1 completed May 3, 2026, 8:48 p.m.
NED2 Entity disambiguation (via description) batch_69f7b5c9e284819094e7af030e1e9034 completed May 3, 2026, 8:53 p.m.
Created at: April 9, 2026, 10:11 p.m.