Triple

T941626
Position Surface form Disambiguated ID Type / Status
Subject Compaq E20318 entity
Predicate foundedBy P104 FINISHED
Object Jim Harris
Jim Harris is a technology executive best known as one of the founders of the computer company Compaq.
E122815 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: Jim Harris | Statement: [Compaq, foundedBy, Jim Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jim Harris
Context triple: [Compaq, foundedBy, Jim Harris]
  • A. John Anglin
    John Anglin was a real-life American bank robber best known as one of the three inmates who carried out the infamous 1962 escape from Alcatraz prison.
  • B. Jeff Sharp
    Jeff Sharp is a film producer known for his work on independent and literary adaptation projects in American cinema.
  • C. Ted Cheesman
    Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
  • D. Murray Costello
    Murray Costello is a Canadian former ice hockey executive and physician best known for his influential leadership in Hockey Canada and international hockey development.
  • E. Tim McClelland
    Tim McClelland is a former Major League Baseball umpire known for his long tenure, distinctive strike zone, and involvement in several high-profile postseason games.
  • 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: Jim Harris
Triple: [Compaq, foundedBy, Jim Harris]
Generated description
Jim Harris is a technology executive best known as one of the founders of the computer company Compaq.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jim Harris
Target entity description: Jim Harris is a technology executive best known as one of the founders of the computer company Compaq.
  • A. John Anglin
    John Anglin was a real-life American bank robber best known as one of the three inmates who carried out the infamous 1962 escape from Alcatraz prison.
  • B. Jeff Sharp
    Jeff Sharp is a film producer known for his work on independent and literary adaptation projects in American cinema.
  • C. Ted Cheesman
    Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
  • D. Murray Costello
    Murray Costello is a Canadian former ice hockey executive and physician best known for his influential leadership in Hockey Canada and international hockey development.
  • E. Tim McClelland
    Tim McClelland is a former Major League Baseball umpire known for his long tenure, distinctive strike zone, and involvement in several high-profile postseason games.
  • 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_69a493b0270c81909e6c9ce310f6aa55 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b38cc6888190b1d9043ec8fbcbc3 completed March 1, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42851b8881908b2625e3cb34cb6c completed March 7, 2026, 3:21 p.m.
NEDg Description generation batch_69ac42f4d51c81908a39c05213da4633 completed March 7, 2026, 3:23 p.m.
NED2 Entity disambiguation (via description) batch_69ac436720a88190b88ffd74956f5bf5 completed March 7, 2026, 3:25 p.m.
Created at: March 1, 2026, 7:40 p.m.