Triple

T6135907
Position Surface form Disambiguated ID Type / Status
Subject First Take E136831 entity
Predicate hasFormerPanelist P5021 FINISHED
Object Max Kellerman
Max Kellerman is an American sports television personality and boxing commentator known for his outspoken analysis on ESPN programs and boxing broadcasts.
E570441 NE FINISHED

How this triple was built (5 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: Max Kellerman | Statement: [First Take, hasFormerPanelist, Max Kellerman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Max Kellerman
Context triple: [First Take, hasFormerPanelist, Max Kellerman]
  • A. Harlan Krumholz
    Harlan Krumholz is an American cardiologist and health outcomes researcher known for his work on quality of care, patient-centered outcomes, and healthcare transparency.
  • B. Paul Prenter
    Paul Prenter was Freddie Mercury’s former personal manager, widely known for his controversial role in Mercury’s life and career, including his portrayal as a key antagonist in the film "Bohemian Rhapsody."
  • C. Lou Carducci
    Lou Carducci is a fictional character played by American actress and model Mackenzie Foy.
  • D. Larry Stenger
    Larry Stenger is one of the original founders associated with the early formation of semiconductor company Advanced Micro Devices (AMD).
  • E. Dr. Mark Greene
    Dr. Mark Greene is a central, long-running emergency physician character on the television drama "ER," known for his compassionate care and personal struggles.
  • 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: Max Kellerman
Triple: [First Take, hasFormerPanelist, Max Kellerman]
Generated description
Max Kellerman is an American sports television personality and boxing commentator known for his outspoken analysis on ESPN programs and boxing broadcasts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Max Kellerman
Target entity description: Max Kellerman is an American sports television personality and boxing commentator known for his outspoken analysis on ESPN programs and boxing broadcasts.
  • A. Harlan Krumholz
    Harlan Krumholz is an American cardiologist and health outcomes researcher known for his work on quality of care, patient-centered outcomes, and healthcare transparency.
  • B. Paul Prenter
    Paul Prenter was Freddie Mercury’s former personal manager, widely known for his controversial role in Mercury’s life and career, including his portrayal as a key antagonist in the film "Bohemian Rhapsody."
  • C. Lou Carducci
    Lou Carducci is a fictional character played by American actress and model Mackenzie Foy.
  • D. Larry Stenger
    Larry Stenger is one of the original founders associated with the early formation of semiconductor company Advanced Micro Devices (AMD).
  • E. Dr. Mark Greene
    Dr. Mark Greene is a central, long-running emergency physician character on the television drama "ER," known for his compassionate care and personal struggles.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFormerPanelist
Context triple: [First Take, hasFormerPanelist, Max Kellerman]
  • A. hasFormerChairperson
    Indicates that an entity previously held the role of chairperson of another entity, but no longer occupies that position.
  • B. hasFormerPatron
    Indicates that an entity previously served as a patron or sponsor of another entity, but no longer holds that role.
  • C. hasFormerLeader
    Indicates that an entity previously held the role of leader of another entity but no longer does.
  • D. hadMember chosen
    Indicates that an entity was formerly a member or part of another entity or group.
  • E. hasParticipants
    Indicates that an event, activity, or situation involves one or more entities as participants in it.
  • F. None of above.

Provenance (6 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_69c008a179388190a3b5a081bbf46d55 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c8211d48190bc10675ba6707150 completed March 22, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135e22b9481908e6023d1b0a5d0fd completed March 23, 2026, 12:45 p.m.
NEDg Description generation batch_69c136545e788190a988f19d5d20c1a4 completed March 23, 2026, 12:47 p.m.
NED2 Entity disambiguation (via description) batch_69c136e1615c8190bcc33362b1182a2f completed March 23, 2026, 12:49 p.m.
PD Predicate disambiguation batch_69c055f19b0c81908be34a00ab218723 completed March 22, 2026, 8:49 p.m.
Created at: March 22, 2026, 4:15 p.m.