Triple

T5532569
Position Surface form Disambiguated ID Type / Status
Subject Narbonne High School E145082 entity
Predicate hasAlumnus P51 FINISHED
Object Jeff Graham
Jeff Graham is an American former NFL wide receiver who played for the Pittsburgh Steelers, Chicago Bears, and several other teams during the 1990s.
 E544755 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: Jeff Graham | Statement: [Narbonne High School, hasAlumnus, Jeff Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jeff Graham
Context triple: [Narbonne High School, hasAlumnus, Jeff Graham]
  • A. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • B. Ed Scott
    Ed Scott is a technology entrepreneur best known as a co-founder of BEA Systems, a major enterprise software company later acquired by Oracle.
  • C. Jeff Gillooly
    Jeff Gillooly is best known as the ex-husband of figure skater Tonya Harding and a central figure in the 1994 attack on her rival Nancy Kerrigan.
  • D. Graham O'Brien
    Graham O'Brien is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
  • E. Sean Kenney
    Sean Kenney is an American actor best known for playing the disfigured Captain Christopher Pike in the original Star Trek series.
  • 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: Jeff Graham
Triple: [Narbonne High School, hasAlumnus, Jeff Graham]
Generated description
Jeff Graham is an American former NFL wide receiver who played for the Pittsburgh Steelers, Chicago Bears, and several other teams during the 1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jeff Graham
Target entity description: Jeff Graham is an American former NFL wide receiver who played for the Pittsburgh Steelers, Chicago Bears, and several other teams during the 1990s.
  • A. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • B. Ed Scott
    Ed Scott is a technology entrepreneur best known as a co-founder of BEA Systems, a major enterprise software company later acquired by Oracle.
  • C. Jeff Gillooly
    Jeff Gillooly is best known as the ex-husband of figure skater Tonya Harding and a central figure in the 1994 attack on her rival Nancy Kerrigan.
  • D. Graham O'Brien
    Graham O'Brien is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
  • E. Sean Kenney
    Sean Kenney is an American actor best known for playing the disfigured Captain Christopher Pike in the original Star Trek series.
  • 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_69c008f9955881909bfa8348b56b4739 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f9ea2c88190a68642f5799bd8ff completed March 22, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07d65dafc819083b60cbff2031819 completed March 22, 2026, 11:38 p.m.
NEDg Description generation batch_69c08a993fbc81908e33c3a623c947b3 completed March 23, 2026, 12:34 a.m.
NED2 Entity disambiguation (via description) batch_69c08ae679588190909474da7e4bed68 completed March 23, 2026, 12:35 a.m.
Created at: March 22, 2026, 3:34 p.m.