Triple

T21357807
Position Surface form Disambiguated ID Type / Status
Subject Sara Paretsky E526681 entity
Predicate notableWork P4 FINISHED
Object Brush Back
Brush Back is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she reopens a decades-old murder case on Chicago’s South Side.
E1480607 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: Brush Back | Statement: [Sara Paretsky, notableWork, Brush Back]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brush Back
Context triple: [Sara Paretsky, notableWork, Brush Back]
  • A. Back to Front
    Back to Front is a compilation album by Lionel Richie that collects some of his most popular solo hits.
  • B. Back to Front
    "Back to Front" is a 1972 studio album by Irish singer-songwriter Gilbert O'Sullivan, featuring his hit single "Clair" and showcasing his melodic pop songwriting style.
  • C. Doubleback
    "Doubleback" is a 1990 blues-rock song by ZZ Top, best known for its prominent feature in the film *Back to the Future Part III*.
  • D. Rollin Back
    "Rollin Back" is a song featured on My Morning Jacket's 2003 album *It Still Moves*.
  • E. Drive Back
    Drive Back is a song featured on the soundtrack of the 2006 racing video game "Zuma."
  • 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: Brush Back
Triple: [Sara Paretsky, notableWork, Brush Back]
Generated description
Brush Back is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she reopens a decades-old murder case on Chicago’s South Side.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brush Back
Target entity description: Brush Back is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she reopens a decades-old murder case on Chicago’s South Side.
  • A. Back to Front
    Back to Front is a compilation album by Lionel Richie that collects some of his most popular solo hits.
  • B. Back to Front
    "Back to Front" is a 1972 studio album by Irish singer-songwriter Gilbert O'Sullivan, featuring his hit single "Clair" and showcasing his melodic pop songwriting style.
  • C. Doubleback
    "Doubleback" is a 1990 blues-rock song by ZZ Top, best known for its prominent feature in the film *Back to the Future Part III*.
  • D. Rollin Back
    "Rollin Back" is a song featured on My Morning Jacket's 2003 album *It Still Moves*.
  • E. Drive Back
    Drive Back is a song featured on the soundtrack of the 2006 racing video game "Zuma."
  • 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_69e0b51d8a308190b09113b3b3f9bc15 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8afa2d11c81908608851940e4e6d3 completed April 22, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09ad65626c819081615b512241fe1c completed May 17, 2026, 11:58 a.m.
NEDg Description generation batch_6a09b14b7694819084b4b391fa821961 completed May 17, 2026, 12:15 p.m.
NED2 Entity disambiguation (via description) batch_6a09b1af3e708190b7b2971db2508f7b completed May 17, 2026, 12:16 p.m.
Created at: April 16, 2026, 5:07 p.m.