Triple

T12171227
Position Surface form Disambiguated ID Type / Status
Subject Trevor Berbick E289970 entity
Predicate familyName P18 FINISHED
Object Berbick
Berbick is the surname of Trevor Berbick, a Jamaican-born heavyweight boxer best known for being the last man to fight and lose the world title to Muhammad Ali.
E967197 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: Berbick | Statement: [Trevor Berbick, familyName, Berbick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berbick
Context triple: [Trevor Berbick, familyName, Berbick]
  • A. Banton
    Banton is a small island municipality in the province of Romblon in the Philippines, known for its rugged terrain, historic church, and preserved indigenous culture.
  • B. Sangster
    Sangster is the surname of English actor Thomas Brodie-Sangster, known for roles in films like "Love Actually" and series such as "Game of Thrones" and "The Queen's Gambit."
  • C. Gonsalves
    Gonsalves is a Portuguese-origin surname commonly found in Lusophone and Caribbean communities.
  • D. Deveraux
    Deveraux is a French-origin surname commonly associated with various real and fictional individuals.
  • E. Warley
    Warley is a locality within the Brentwood Borough of Essex, England, known primarily as a residential suburb with historical military and institutional connections.
  • 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: Berbick
Triple: [Trevor Berbick, familyName, Berbick]
Generated description
Berbick is the surname of Trevor Berbick, a Jamaican-born heavyweight boxer best known for being the last man to fight and lose the world title to Muhammad Ali.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Berbick
Target entity description: Berbick is the surname of Trevor Berbick, a Jamaican-born heavyweight boxer best known for being the last man to fight and lose the world title to Muhammad Ali.
  • A. Banton
    Banton is a small island municipality in the province of Romblon in the Philippines, known for its rugged terrain, historic church, and preserved indigenous culture.
  • B. Sangster
    Sangster is the surname of English actor Thomas Brodie-Sangster, known for roles in films like "Love Actually" and series such as "Game of Thrones" and "The Queen's Gambit."
  • C. Gonsalves
    Gonsalves is a Portuguese-origin surname commonly found in Lusophone and Caribbean communities.
  • D. Deveraux
    Deveraux is a French-origin surname commonly associated with various real and fictional individuals.
  • E. Warley
    Warley is a locality within the Brentwood Borough of Essex, England, known primarily as a residential suburb with historical military and institutional connections.
  • 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_69d6ab4d6c00819095a9a7c35de83cfb completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915d9659481909c75b12aa836bbf3 completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f6a6de3081908e5e0030c081d5a4 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f603b639208190a284fcd7e88e9d54 completed May 2, 2026, 2:01 p.m.
NED2 Entity disambiguation (via description) batch_69f60491eaec8190a16472fd37740ea0 completed May 2, 2026, 2:05 p.m.
Created at: April 8, 2026, 9:50 p.m.