Triple

T12926093
Position Surface form Disambiguated ID Type / Status
Subject Before He Cheats E309247 entity
Predicate writer P1360 FINISHED
Object Chris Tompkins
Chris Tompkins is an American songwriter best known for co-writing major country and pop hits, including Carrie Underwood’s smash single "Before He Cheats."
 E1012243 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: Chris Tompkins | Statement: [Before He Cheats, writer, Chris Tompkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Chris Tompkins
Context triple: [Before He Cheats, writer, Chris Tompkins]
  • A. Tully Friedman
    Tully Friedman is an American financier and private equity investor best known as the co-founder of the investment firm Hellman & Friedman.
  • B. Gil Robbins
    Gil Robbins was an American folk musician and actor, best known as a member of the Highwaymen and for his work in the 1960s folk scene.
  • C. Laurie Tisch
    Laurie Tisch is an American philanthropist and arts patron known for her significant contributions to education, culture, and community initiatives in New York City.
  • D. Lee Stimmel
    Lee Stimmel is a television writer and producer best known for co-creating the animated comedy series "Mike Tyson Mysteries."
  • E. Kay Nelson
    Kay Nelson was a Hollywood costume designer known for her work on classic films of the 1940s.
  • 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: Chris Tompkins
Triple: [Before He Cheats, writer, Chris Tompkins]
Generated description
Chris Tompkins is an American songwriter best known for co-writing major country and pop hits, including Carrie Underwood’s smash single "Before He Cheats."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Chris Tompkins
Target entity description: Chris Tompkins is an American songwriter best known for co-writing major country and pop hits, including Carrie Underwood’s smash single "Before He Cheats."
  • A. Tully Friedman
    Tully Friedman is an American financier and private equity investor best known as the co-founder of the investment firm Hellman & Friedman.
  • B. Gil Robbins
    Gil Robbins was an American folk musician and actor, best known as a member of the Highwaymen and for his work in the 1960s folk scene.
  • C. Lee Stimmel
    Lee Stimmel is a television writer and producer best known for co-creating the animated comedy series "Mike Tyson Mysteries."
  • D. Kay Nelson
    Kay Nelson was a Hollywood costume designer known for her work on classic films of the 1940s.
  • E. Tracy Hoffman
    Tracy Hoffman is best known as the wife of former Major League Baseball All-Star closer Trevor Hoffman.
  • 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_69d7bdfa933c8190b5a27aa4a08a19b7 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971eb17c88190bf523da897172a0c completed April 10, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af64905c8190b0f2adb66c17c476 completed May 3, 2026, 2:13 a.m.
NEDg Description generation batch_69f6b19fbe3881909e08628c0672388b completed May 3, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_69f6b5d11960819092c920f19eaad540 completed May 3, 2026, 2:41 a.m.
Created at: April 9, 2026, 5:42 p.m.