Triple

T5042119
Position Surface form Disambiguated ID Type / Status
Subject The Killing E113568 entity
Predicate basedOn P98 FINISHED
Object Clean Break
Clean Break is a 2008 crime novel by Scottish author Val McDermid featuring journalist Lindsay Gordon, which served as the basis for the Danish TV series "The Killing."
 E488538 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: Clean Break | Statement: [The Killing, basedOn, Clean Break]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Clean Break
Context triple: [The Killing, basedOn, Clean Break]
  • A. The Break-Up
    The Break-Up is a 2006 romantic comedy-drama film starring Jennifer Aniston and Vince Vaughn as a couple navigating a messy split while still sharing their condo.
  • B. Breaking Us in Two
    "Breaking Us in Two" is a melodic pop-rock ballad by English musician Joe Jackson, released in the early 1980s and known for its reflective lyrics and prominent use of piano.
  • C. Break Up
    "Break Up" is a song by American R&B singer Mario, best known for its smooth production and themes of romantic conflict and separation.
  • D. Don’t Break It
    Don’t Break It is a track featured on the jazz standard album "All of Me."
  • E. Break It Off
    "Break It Off" is a dancehall-infused pop song by Rihanna featuring Sean Paul, known for its upbeat rhythm and Caribbean flair.
  • 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: Clean Break
Triple: [The Killing, basedOn, Clean Break]
Generated description
Clean Break is a 2008 crime novel by Scottish author Val McDermid featuring journalist Lindsay Gordon, which served as the basis for the Danish TV series "The Killing."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Clean Break
Target entity description: Clean Break is a 2008 crime novel by Scottish author Val McDermid featuring journalist Lindsay Gordon, which served as the basis for the Danish TV series "The Killing."
  • A. The Break-Up
    The Break-Up is a 2006 romantic comedy-drama film starring Jennifer Aniston and Vince Vaughn as a couple navigating a messy split while still sharing their condo.
  • B. Breaking Us in Two
    "Breaking Us in Two" is a melodic pop-rock ballad by English musician Joe Jackson, released in the early 1980s and known for its reflective lyrics and prominent use of piano.
  • C. Break Up
    "Break Up" is a song by American R&B singer Mario, best known for its smooth production and themes of romantic conflict and separation.
  • D. Don’t Break It
    Don’t Break It is a track featured on the jazz standard album "All of Me."
  • E. Break It Off
    "Break It Off" is a dancehall-infused pop song by Rihanna featuring Sean Paul, known for its upbeat rhythm and Caribbean flair.
  • 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_69bd44384298819089c49e7c330ec7b8 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73df8f7481909a8b86c4ae69aab9 completed March 20, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9c8414288190bf53a40033aa70ea completed March 21, 2026, 1:26 p.m.
NEDg Description generation batch_69be9e5bc02c8190bcb1442439673706 completed March 21, 2026, 1:34 p.m.
NED2 Entity disambiguation (via description) batch_69be9f0888cc8190bfed8337e15ca909 completed March 21, 2026, 1:37 p.m.
Created at: March 20, 2026, 1:37 p.m.