Triple

T5214384
Position Surface form Disambiguated ID Type / Status
Subject Zoe Saldana E117712 entity
Predicate spouse P13 FINISHED
Object Marco Perego-Saldaña
Marco Perego-Saldaña is an Italian artist and former professional soccer player who is married to actress Zoe Saldaña.
E507000 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: Marco Perego-Saldaña | Statement: [Zoe Saldana, spouse, Marco Perego-Saldaña]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marco Perego-Saldaña
Context triple: [Zoe Saldana, spouse, Marco Perego-Saldaña]
  • A. Andrés Saliquet
    Andrés Saliquet was a Spanish Nationalist general during the Spanish Civil War who held several key commands in major campaigns.
  • B. Sebastián Pozas
    Sebastián Pozas was a Spanish Republican general and senior military commander during the Spanish Civil War.
  • C. Fernando Grediaga
    Fernando Grediaga is a Mexican actor best known for his role in Alfonso Cuarón’s acclaimed film "Roma" (2018).
  • D. Nicolás Sánchez
    Nicolás Sánchez is an Argentine rugby union fly-half renowned for his prolific goal-kicking and playmaking, notably starring as the leading points scorer at the 2015 Rugby World Cup.
  • E. Artur Paredes
    Artur Paredes was a seminal Portuguese guitarist and composer who modernized the Coimbra style of fado and influenced generations of fado musicians.
  • 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: Marco Perego-Saldaña
Triple: [Zoe Saldana, spouse, Marco Perego-Saldaña]
Generated description
Marco Perego-Saldaña is an Italian artist and former professional soccer player who is married to actress Zoe Saldaña.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marco Perego-Saldaña
Target entity description: Marco Perego-Saldaña is an Italian artist and former professional soccer player who is married to actress Zoe Saldaña.
  • A. Andrés Saliquet
    Andrés Saliquet was a Spanish Nationalist general during the Spanish Civil War who held several key commands in major campaigns.
  • B. Sebastián Pozas
    Sebastián Pozas was a Spanish Republican general and senior military commander during the Spanish Civil War.
  • C. Fernando Grediaga
    Fernando Grediaga is a Mexican actor best known for his role in Alfonso Cuarón’s acclaimed film "Roma" (2018).
  • D. Nicolás Sánchez
    Nicolás Sánchez is an Argentine rugby union fly-half renowned for his prolific goal-kicking and playmaking, notably starring as the leading points scorer at the 2015 Rugby World Cup.
  • E. Artur Paredes
    Artur Paredes was a seminal Portuguese guitarist and composer who modernized the Coimbra style of fado and influenced generations of fado musicians.
  • 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_69bd4464ba3c8190bc16b2ebbe42ddb0 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a911d40819086621537274dc0f0 completed March 20, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69befe5aabbc8190bc09eaffb5ec9776 completed March 21, 2026, 8:23 p.m.
NEDg Description generation batch_69beff0dda548190831d34282afa9b8e completed March 21, 2026, 8:26 p.m.
NED2 Entity disambiguation (via description) batch_69beff6890f4819088cb053bcdb4f8a1 completed March 21, 2026, 8:28 p.m.
Created at: March 20, 2026, 1:47 p.m.