Triple

T16827387
Position Surface form Disambiguated ID Type / Status
Subject San Francisco Demons E409055 entity
Predicate generalManager P537 FINISHED
Object Michael Keller
Michael Keller is a sports executive best known for serving as the general manager of the XFL’s San Francisco Demons football team.
 E1260796 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: Michael Keller | Statement: [San Francisco Demons, generalManager, Michael Keller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Michael Keller
Context triple: [San Francisco Demons, generalManager, Michael Keller]
  • A. Michael Keller
    Michael Keller is an individual known for his role in establishing the Long Now Foundation, an organization dedicated to promoting long-term thinking and responsibility.
  • B. Jason Keller
    Jason Keller is an American screenwriter best known for co-writing the racing drama film "Ford v Ferrari."
  • C. Aidan Keller
    Aidan Keller is the young, psychically sensitive boy central to the plot of the horror film "The Ring."
  • D. Keith Keller
    Keith Keller is a film industry figure best known as a co-founder of the Seattle International Film Festival, one of the largest and most respected film festivals in the United States.
  • E. Tim Kehler
    Tim Kehler is a Canadian professional ice hockey coach known for his work behind the bench in various European and North American leagues.
  • 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: Michael Keller
Triple: [San Francisco Demons, generalManager, Michael Keller]
Generated description
Michael Keller is a sports executive best known for serving as the general manager of the XFL’s San Francisco Demons football team.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Michael Keller
Target entity description: Michael Keller is a sports executive best known for serving as the general manager of the XFL’s San Francisco Demons football team.
  • A. Michael Keller
    Michael Keller is an individual known for his role in establishing the Long Now Foundation, an organization dedicated to promoting long-term thinking and responsibility.
  • B. Jason Keller
    Jason Keller is an American screenwriter best known for co-writing the racing drama film "Ford v Ferrari."
  • C. Aidan Keller
    Aidan Keller is the young, psychically sensitive boy central to the plot of the horror film "The Ring."
  • D. Keith Keller
    Keith Keller is a film industry figure best known as a co-founder of the Seattle International Film Festival, one of the largest and most respected film festivals in the United States.
  • E. Tim Kehler
    Tim Kehler is a Canadian professional ice hockey coach known for his work behind the bench in various European and North American leagues.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b31404c88190a3b2802842ca77eb completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a017932fd5481909bf3c63409fd6da6 completed May 11, 2026, 6:37 a.m.
NEDg Description generation batch_6a017d46a0b88190a016ae624d6f4dd4 completed May 11, 2026, 6:55 a.m.
NED2 Entity disambiguation (via description) batch_6a017dc25d648190ab5031ee8ad09d91 completed May 11, 2026, 6:57 a.m.
Created at: April 10, 2026, 5:23 a.m.