Triple

T21357796
Position Surface form Disambiguated ID Type / Status
Subject Sara Paretsky E526681 entity
Predicate notableWork P4 FINISHED
Object Burn Marks
Burn Marks is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she uncovers corruption and arson in Chicago.
E1480597 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: Burn Marks | Statement: [Sara Paretsky, notableWork, Burn Marks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burn Marks
Context triple: [Sara Paretsky, notableWork, Burn Marks]
  • A. Burnmouth
    Burnmouth is a small coastal village in the Scottish Borders, known for its picturesque harbour and dramatic cliffs along the North Sea.
  • B. Burnt
    Burnt is a 2015 drama-comedy film about a talented but troubled chef seeking redemption in the high-pressure world of haute cuisine.
  • C. Burn
    Burn is the first name of Burn Gorman, a British-American actor known for roles in productions such as "Torchwood," "Game of Thrones," and "Pacific Rim."
  • D. Burn
    "Burn" is a song by the American rock band Yeah! that was released as the follow-up single to their track "Yeah!"
  • E. Burn
    Burn is a 1974 hard rock album by the English band Deep Purple, marking the debut of their Mk III lineup with David Coverdale and Glenn Hughes.
  • 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: Burn Marks
Triple: [Sara Paretsky, notableWork, Burn Marks]
Generated description
Burn Marks is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she uncovers corruption and arson in Chicago.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Burn Marks
Target entity description: Burn Marks is a crime novel by Sara Paretsky featuring her iconic private investigator V.I. Warshawski as she uncovers corruption and arson in Chicago.
  • A. Burnmouth
    Burnmouth is a small coastal village in the Scottish Borders, known for its picturesque harbour and dramatic cliffs along the North Sea.
  • B. Burnt
    Burnt is a 2015 drama-comedy film about a talented but troubled chef seeking redemption in the high-pressure world of haute cuisine.
  • C. Burn
    "Burn" is a song by the American rock band Yeah! that was released as the follow-up single to their track "Yeah!"
  • D. Burn
    Burn is the first name of Burn Gorman, a British-American actor known for roles in productions such as "Torchwood," "Game of Thrones," and "Pacific Rim."
  • E. Burn
    Burn is the abbreviated name of the former Major League Soccer team Dallas Burn, now known as FC Dallas.
  • 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.