Triple

T8078547
Position Surface form Disambiguated ID Type / Status
Subject Ferrari F2004 E188556 entity
Predicate designer P184 FINISHED
Object Aldo Costa
Aldo Costa is an Italian motorsport engineer renowned for designing multiple championship-winning Formula One cars for teams such as Ferrari and Mercedes.
E849351 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: Aldo Costa | Statement: [Ferrari F2004, designer, Aldo Costa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aldo Costa
Context triple: [Ferrari F2004, designer, Aldo Costa]
  • A. Ernesto Rossi
    Ernesto Rossi was an Italian anti-fascist activist, journalist, and politician best known for co-authoring the Ventotene Manifesto, a foundational text of European federalism.
  • B. Aldo Bonnadonna
    Aldo Bonnadonna is a fictional character appearing in the television series "Kristin."
  • C. Lino Lacedelli
    Lino Lacedelli was an Italian mountaineer best known for being one of the first climbers to reach the summit of K2 in 1954.
  • D. Guido Molinari
    Guido Molinari was a Canadian abstract painter renowned for his hard-edge geometric compositions and influential role in the development of modern art in Quebec.
  • E. Roberto Silvi
    Roberto Silvi is a film editor known for his work on movies such as the 1972 comedy-drama "Pete 'n' Tillie."
  • 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: Aldo Costa
Triple: [Ferrari F2004, designer, Aldo Costa]
Generated description
Aldo Costa is an Italian motorsport engineer renowned for designing multiple championship-winning Formula One cars for teams such as Ferrari and Mercedes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Aldo Costa
Target entity description: Aldo Costa is an Italian motorsport engineer renowned for designing multiple championship-winning Formula One cars for teams such as Ferrari and Mercedes.
  • A. Ernesto Rossi
    Ernesto Rossi was an Italian anti-fascist activist, journalist, and politician best known for co-authoring the Ventotene Manifesto, a foundational text of European federalism.
  • B. Aldo Bonnadonna
    Aldo Bonnadonna is a fictional character appearing in the television series "Kristin."
  • C. Lino Lacedelli
    Lino Lacedelli was an Italian mountaineer best known for being one of the first climbers to reach the summit of K2 in 1954.
  • D. Guido Molinari
    Guido Molinari was a Canadian abstract painter renowned for his hard-edge geometric compositions and influential role in the development of modern art in Quebec.
  • E. Roberto Silvi
    Roberto Silvi is a film editor known for his work on movies such as the 1972 comedy-drama "Pete 'n' Tillie."
  • 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_69ca82b50c708190863f661d438e68df completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb40a2b64c8190ae2b3414b4f840e4 completed March 31, 2026, 3:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69d642c457f08190a79c7161ceadb869 completed April 8, 2026, 11:57 a.m.
NEDg Description generation batch_69d643b2e7408190ba0c6fbe8f9ece1a completed April 8, 2026, 12:01 p.m.
NED2 Entity disambiguation (via description) batch_69d644090ad0819083a2f59860134526 completed April 8, 2026, 12:03 p.m.
Created at: March 30, 2026, 5:28 p.m.