Triple

T17714857
Position Surface form Disambiguated ID Type / Status
Subject Home Improvement E442168 entity
Predicate character P662 FINISHED
Object Al Borland
Al Borland is the flannel-wearing, level-headed co-host and skilled handyman on the fictional TV show-within-a-show "Tool Time" in the sitcom *Home Improvement*.
E1284395 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: Al Borland | Statement: [Home Improvement, character, Al Borland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Al Borland
Context triple: [Home Improvement, character, Al Borland]
  • A. Allen Bonet
    Allen Bonet was the father of American actress Lisa Bonet and is primarily known to the public through this familial connection.
  • B. Roger Borsa
    Roger Borsa was an 11th-century Norman duke who ruled Apulia and Calabria in southern Italy, succeeding his father Robert Guiscard.
  • C. Steve Lombard
    Steve Lombard is a fictional sports editor and former football star in DC Comics, best known as a brash, prank-loving colleague of Clark Kent at the Daily Planet.
  • D. Adam Bulgasem
    Adam Bulgasem is a musician known for being a member of the experimental rock band Black Mountain.
  • E. Robert Paparemborde
    Robert Paparemborde was a prominent French rugby union prop who earned numerous caps for France and became one of the standout forwards of his era.
  • 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: Al Borland
Triple: [Home Improvement, character, Al Borland]
Generated description
Al Borland is the flannel-wearing, level-headed co-host and skilled handyman on the fictional TV show-within-a-show "Tool Time" in the sitcom *Home Improvement*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Al Borland
Target entity description: Al Borland is the flannel-wearing, level-headed co-host and skilled handyman on the fictional TV show-within-a-show "Tool Time" in the sitcom *Home Improvement*.
  • A. Allen Bonet
    Allen Bonet was the father of American actress Lisa Bonet and is primarily known to the public through this familial connection.
  • B. Roger Borsa
    Roger Borsa was an 11th-century Norman duke who ruled Apulia and Calabria in southern Italy, succeeding his father Robert Guiscard.
  • C. Steve Lombard
    Steve Lombard is a fictional sports editor and former football star in DC Comics, best known as a brash, prank-loving colleague of Clark Kent at the Daily Planet.
  • D. Adam Bulgasem
    Adam Bulgasem is a musician known for being a member of the experimental rock band Black Mountain.
  • E. Robert Paparemborde
    Robert Paparemborde was a prominent French rugby union prop who earned numerous caps for France and became one of the standout forwards of his era.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4747f217081909010f396caaf03be completed April 19, 2026, 6:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a023029aa808190bfacd42036a2f673 completed May 11, 2026, 7:38 p.m.
NEDg Description generation batch_6a0231835c748190b6908d6ddb5f25b4 completed May 11, 2026, 7:44 p.m.
NED2 Entity disambiguation (via description) batch_6a0232033f788190b0be2d3976ed57e4 completed May 11, 2026, 7:46 p.m.
Created at: April 10, 2026, 10:06 a.m.