Triple

T11024829
Position Surface form Disambiguated ID Type / Status
Subject Overbrook High School E260591 entity
Predicate notableAlumnus P304 FINISHED
Object Hal Lear
Hal Lear was an American professional basketball player best known as a standout guard at Temple University in the 1950s and a member of the Philadelphia Big 5 Hall of Fame.
E900480 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: Hal Lear | Statement: [Overbrook High School, notableAlumnus, Hal Lear]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hal Lear
Context triple: [Overbrook High School, notableAlumnus, Hal Lear]
  • A. Tom Hallion
    Tom Hallion is a veteran Major League Baseball umpire known for his long career and distinctive strike call.
  • B. Herb Tarlek
    Herb Tarlek is a loud, tacky-suited, and comically inept advertising salesman character from the WKRP in Cincinnati television franchise.
  • C. Kenith Trodd
    Kenith Trodd is a British television producer best known for his collaborations with writer Dennis Potter on acclaimed dramas such as "The Singing Detective."
  • D. Hal
    Hal is a masculine given name, commonly used as a diminutive form of Harold.
  • E. Ridley
    Ridley is the given name of the renowned British film director and producer Ridley Scott.
  • 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: Hal Lear
Triple: [Overbrook High School, notableAlumnus, Hal Lear]
Generated description
Hal Lear was an American professional basketball player best known as a standout guard at Temple University in the 1950s and a member of the Philadelphia Big 5 Hall of Fame.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hal Lear
Target entity description: Hal Lear was an American professional basketball player best known as a standout guard at Temple University in the 1950s and a member of the Philadelphia Big 5 Hall of Fame.
  • A. Tom Hallion
    Tom Hallion is a veteran Major League Baseball umpire known for his long career and distinctive strike call.
  • B. Herb Tarlek
    Herb Tarlek is a loud, tacky-suited, and comically inept advertising salesman character from the WKRP in Cincinnati television franchise.
  • C. Kenith Trodd
    Kenith Trodd is a British television producer best known for his collaborations with writer Dennis Potter on acclaimed dramas such as "The Singing Detective."
  • D. Hal
    Hal is a masculine given name, commonly used as a diminutive form of Harold.
  • E. Ridley
    Ridley is the given name of the renowned British film director and producer Ridley Scott.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797bf78a48190a37b423812827d4e completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e37523f8548190ad40fa76660232a8 completed April 18, 2026, 12:12 p.m.
NEDg Description generation batch_69e37ab860f48190808ba0076cfa9c98 completed April 18, 2026, 12:36 p.m.
NED2 Entity disambiguation (via description) batch_69e3864dd0d48190b3fd81381f5d7418 completed April 18, 2026, 1:25 p.m.
Created at: April 8, 2026, 9:25 p.m.