Triple

T11994243
Position Surface form Disambiguated ID Type / Status
Subject George Luz E285486 entity
Predicate unitComrades P102772 FINISHED
Object Lynn Compton
Lynn "Buck" Compton was a U.S. Army officer in Easy Company of the 101st Airborne Division during World War II who later became a prosecutor and judge in California.
 E958681 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: Lynn Compton | Statement: [George Luz, unitComrades, Lynn Compton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lynn Compton
Context triple: [George Luz, unitComrades, Lynn Compton]
  • A. Lynn Boyle
    Lynn Boyle is a character in the television series "Brooklyn Nine-Nine," known as one of Charles Boyle’s eccentric and overly affectionate family members.
  • B. Judy Campbell
    Judy Campbell was a British actress known for her stage and film work in the mid-20th century, particularly in plays by Noël Coward.
  • C. Gail Lyon
    Gail Lyon is a film producer best known for her work on the gymnastics-themed comedy-drama movie "Stick It."
  • D. Lynne Frederick
    Lynne Frederick was a British actress and model best known for her film roles in the 1970s and for being the last wife of comedian Peter Sellers.
  • E. Cynthia Millar
    Cynthia Millar is a British composer and ondes Martenot specialist known for her work on numerous film and television scores.
  • 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: Lynn Compton
Triple: [George Luz, unitComrades, Lynn Compton]
Generated description
Lynn "Buck" Compton was a U.S. Army officer in Easy Company of the 101st Airborne Division during World War II who later became a prosecutor and judge in California.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lynn Compton
Target entity description: Lynn "Buck" Compton was a U.S. Army officer in Easy Company of the 101st Airborne Division during World War II who later became a prosecutor and judge in California.
  • A. Lynn Boyle
    Lynn Boyle is a character in the television series "Brooklyn Nine-Nine," known as one of Charles Boyle’s eccentric and overly affectionate family members.
  • B. Judy Campbell
    Judy Campbell was a British actress known for her stage and film work in the mid-20th century, particularly in plays by Noël Coward.
  • C. Gail Lyon
    Gail Lyon is a film producer best known for her work on the gymnastics-themed comedy-drama movie "Stick It."
  • D. Lynne Frederick
    Lynne Frederick was a British actress and model best known for her film roles in the 1970s and for being the last wife of comedian Peter Sellers.
  • E. Cynthia Millar
    Cynthia Millar is a British composer and ondes Martenot specialist known for her work on numerous film and television scores.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915124e4c8190b0264c2a09e3c2f3 completed April 10, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f47273e1088190b899071baff1375a completed May 1, 2026, 9:29 a.m.
NEDg Description generation batch_69f47b7d4ef081908f7f87d90c00d9ed completed May 1, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_69f47de8c9e48190af01918c9cd94c7d completed May 1, 2026, 10:18 a.m.
Created at: April 8, 2026, 9:46 p.m.