Triple

T23166021
Position Surface form Disambiguated ID Type / Status
Subject Sanford MMA E578712 entity
Predicate hasCoach P2169 FINISHED
Object Kami Barzini
Kami Barzini is a mixed martial arts coach known for training high-level fighters at the renowned Sanford MMA gym.
E1574967 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: Kami Barzini | Statement: [Sanford MMA, hasCoach, Kami Barzini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kami Barzini
Context triple: [Sanford MMA, hasCoach, Kami Barzini]
  • A. Taha Niwas
    Taha Niwas is a historic residence associated with the Afzal Mahal complex, reflecting the architectural and cultural heritage of its period.
  • B. Ben Gashir
    Ben Gashir is a district of Tripoli, Libya, situated near the city’s main international airport.
  • C. Mino Roli
    Mino Roli is an Italian screenwriter known for his work on the 1976 Spaghetti Western film "Keoma."
  • D. Beni Yadjis
    Beni Yadjis is a town and commune located in Jijel Province in northeastern Algeria.
  • E. Philip Barantini
    Philip Barantini is a British actor-turned-filmmaker best known for directing the intense, single-take restaurant drama film "Boiling Point."
  • 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: Kami Barzini
Triple: [Sanford MMA, hasCoach, Kami Barzini]
Generated description
Kami Barzini is a mixed martial arts coach known for training high-level fighters at the renowned Sanford MMA gym.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kami Barzini
Target entity description: Kami Barzini is a mixed martial arts coach known for training high-level fighters at the renowned Sanford MMA gym.
  • A. Taha Niwas
    Taha Niwas is a historic residence associated with the Afzal Mahal complex, reflecting the architectural and cultural heritage of its period.
  • B. Ben Gashir
    Ben Gashir is a district of Tripoli, Libya, situated near the city’s main international airport.
  • C. Mino Roli
    Mino Roli is an Italian screenwriter known for his work on the 1976 Spaghetti Western film "Keoma."
  • D. Beni Yadjis
    Beni Yadjis is a town and commune located in Jijel Province in northeastern Algeria.
  • E. Philip Barantini
    Philip Barantini is a British actor-turned-filmmaker best known for directing the intense, single-take restaurant drama film "Boiling Point."
  • 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_69e245fc75348190a0288401044c8af8 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f2bca4881909f6148d588948018 completed April 29, 2026, 4:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c30a6d7488190aacd5aa205beb9b5 completed May 19, 2026, 9:43 a.m.
NEDg Description generation batch_6a0c34833c048190b8c8372cb58a9538 completed May 19, 2026, 9:59 a.m.
NED2 Entity disambiguation (via description) batch_6a0c3551922481908520bf706ad8d7eb completed May 19, 2026, 10:02 a.m.
Created at: April 17, 2026, 4:03 p.m.