Triple

T20418470
Position Surface form Disambiguated ID Type / Status
Subject Lipstick on Your Collar E500777 entity
Predicate writer P1360 FINISHED
Object George Goehring
George Goehring was an American songwriter best known for co-writing the 1950s rock and roll hit "Lipstick on Your Collar."
E1538083 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: George Goehring | Statement: [Lipstick on Your Collar, writer, George Goehring]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Goehring
Context triple: [Lipstick on Your Collar, writer, George Goehring]
  • A. Charles Rettig
    Charles Rettig is an American tax attorney who served as the Commissioner of the Internal Revenue Service (IRS) from 2018 to 2022.
  • B. George Boemler
    George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
  • C. George Gebhardt
    George Gebhardt was a German-born American silent film actor known for his frequent collaborations with director D. W. Griffith in early 20th-century cinema.
  • D. George Weisgerber
    George Weisgerber is an American reality television personality best known for appearing as a contestant on the VH1 dating show "I Love New York 2."
  • E. Karl Nehring
    Karl Nehring is an American writer and music critic known for his work on classical music and audio reviewing.
  • 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: George Goehring
Triple: [Lipstick on Your Collar, writer, George Goehring]
Generated description
George Goehring was an American songwriter best known for co-writing the 1950s rock and roll hit "Lipstick on Your Collar."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George Goehring
Target entity description: George Goehring was an American songwriter best known for co-writing the 1950s rock and roll hit "Lipstick on Your Collar."
  • A. Charles Rettig
    Charles Rettig is an American tax attorney who served as the Commissioner of the Internal Revenue Service (IRS) from 2018 to 2022.
  • B. George Boemler
    George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
  • C. George Gebhardt
    George Gebhardt was a German-born American silent film actor known for his frequent collaborations with director D. W. Griffith in early 20th-century cinema.
  • D. George Weisgerber
    George Weisgerber is an American reality television personality best known for appearing as a contestant on the VH1 dating show "I Love New York 2."
  • E. Karl Nehring
    Karl Nehring is an American writer and music critic known for his work on classical music and audio reviewing.
  • 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a4686a48190a808c86aa916ad56 completed April 20, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0b0c5343a88190b48e4beca0e779aa completed May 18, 2026, 12:55 p.m.
NEDg Description generation batch_6a0b0ce561e88190b1cd82bb7786f296 completed May 18, 2026, 12:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0b0d9ce0148190b0cda6c97b84d399 completed May 18, 2026, 1:01 p.m.
Created at: April 16, 2026, 11:30 a.m.