Triple

T4151497
Position Surface form Disambiguated ID Type / Status
Subject Sophia Loren E89915 entity
Predicate child P120 FINISHED
Object Edoardo Ponti
Edoardo Ponti is an Italian film director, screenwriter, and producer known for his work in both European and American cinema.
E433995 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: Edoardo Ponti | Statement: [Sophia Loren, child, Edoardo Ponti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edoardo Ponti
Context triple: [Sophia Loren, child, Edoardo Ponti]
  • A. Alfredo Guzzoni
    Alfredo Guzzoni was an Italian army general who commanded Axis forces in Sicily during World War II.
  • B. Marcello Gandini
    Marcello Gandini is an Italian automotive designer renowned for his innovative and angular designs for brands such as Lamborghini, Lancia, and Citroën.
  • C. Carlo Broggi
    Carlo Broggi was an Italian architect best known for his role in designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • D. Enrico Forlanini
    Enrico Forlanini was an Italian engineer and aviation pioneer known for his early work on helicopters, airships, and hydrofoils.
  • E. Luciano Vincenzoni
    Luciano Vincenzoni was an Italian screenwriter best known for his work on classic Spaghetti Westerns, particularly collaborations with director Sergio Leone.
  • 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: Edoardo Ponti
Triple: [Sophia Loren, child, Edoardo Ponti]
Generated description
Edoardo Ponti is an Italian film director, screenwriter, and producer known for his work in both European and American cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Edoardo Ponti
Target entity description: Edoardo Ponti is an Italian film director, screenwriter, and producer known for his work in both European and American cinema.
  • A. Alfredo Guzzoni
    Alfredo Guzzoni was an Italian army general who commanded Axis forces in Sicily during World War II.
  • B. Marcello Gandini
    Marcello Gandini is an Italian automotive designer renowned for his innovative and angular designs for brands such as Lamborghini, Lancia, and Citroën.
  • C. Carlo Broggi
    Carlo Broggi was an Italian architect best known for his role in designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • D. Enrico Forlanini
    Enrico Forlanini was an Italian engineer and aviation pioneer known for his early work on helicopters, airships, and hydrofoils.
  • E. Luciano Vincenzoni
    Luciano Vincenzoni was an Italian screenwriter best known for his work on classic Spaghetti Westerns, particularly collaborations with director Sergio Leone.
  • 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_69aed95a59a881909b26e70b42c6811a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0276363081908e4d17684291b547 completed March 9, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db77e7d88190a7ba250972e133fa completed March 14, 2026, 10:04 p.m.
NEDg Description generation batch_69b5dc3d81a08190b29b633009fab4ff completed March 14, 2026, 10:07 p.m.
NED2 Entity disambiguation (via description) batch_69b5e04f356c81909e3f6f2c865e0f99 completed March 14, 2026, 10:25 p.m.
Created at: March 9, 2026, 3:44 p.m.