Triple

T10583231
Position Surface form Disambiguated ID Type / Status
Subject Scarface E249787 entity
Predicate character P662 FINISHED
Object Frank Lopez
Frank Lopez is a fictional Miami drug lord and early mentor-turned-rival to Tony Montana in the 1983 crime film "Scarface."
E876938 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: Frank Lopez | Statement: [Scarface, character, Frank Lopez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Lopez
Context triple: [Scarface, character, Frank Lopez]
  • A. Al Lopez
    Al Lopez was a Hall of Fame Major League Baseball manager and former catcher best known for leading the Cleveland Indians and Chicago White Sox to American League pennants in the 1950s and early 1960s.
  • B. David Mendoza
    David Mendoza was a composer and conductor active in early 20th-century cinema, known for his work on silent film scores.
  • C. Luis Lopez-Fitzgerald
    Luis Lopez-Fitzgerald is a central romantic lead and heroic police officer in the American soap opera "Passions," known for his tumultuous relationships and family drama.
  • D. Frank Dominguez
    Frank Dominguez is an entrepreneur best known as a founder of the cloud-based software company Salesforce.
  • E. Frank Dominguez
    Frank Dominguez is a person whose specific public background or notable achievements are not clearly identifiable from the given information.
  • 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: Frank Lopez
Triple: [Scarface, character, Frank Lopez]
Generated description
Frank Lopez is a fictional Miami drug lord and early mentor-turned-rival to Tony Montana in the 1983 crime film "Scarface."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank Lopez
Target entity description: Frank Lopez is a fictional Miami drug lord and early mentor-turned-rival to Tony Montana in the 1983 crime film "Scarface."
  • A. Al Lopez
    Al Lopez was a Hall of Fame Major League Baseball manager and former catcher best known for leading the Cleveland Indians and Chicago White Sox to American League pennants in the 1950s and early 1960s.
  • B. David Mendoza
    David Mendoza was a composer and conductor active in early 20th-century cinema, known for his work on silent film scores.
  • C. Luis Lopez-Fitzgerald
    Luis Lopez-Fitzgerald is a central romantic lead and heroic police officer in the American soap opera "Passions," known for his tumultuous relationships and family drama.
  • D. Frank Dominguez
    Frank Dominguez is an entrepreneur best known as a founder of the cloud-based software company Salesforce.
  • E. Frank Dominguez
    Frank Dominguez is a person whose specific public background or notable achievements are not clearly identifiable from the given information.
  • 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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d52767d2e0819099511e29e254bc34 completed April 7, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69d97a1bba1c8190af5a078f40f3bc0a completed April 10, 2026, 10:30 p.m.
NEDg Description generation batch_69d97c7bc87481908d50eb6f294170eb completed April 10, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69d97e015b088190a97822675eecaa5a completed April 10, 2026, 10:47 p.m.
Created at: April 6, 2026, 12:39 p.m.