Triple

T17186206
Position Surface form Disambiguated ID Type / Status
Subject Drums and Guns E417114 entity
Predicate hasTrack P3284 FINISHED
Object Dust on the Window
"Dust on the Window" is a song by the American indie rock band Low from their album "Drums and Guns," known for its sparse, haunting sound and introspective mood.
 E1255875 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: Dust on the Window | Statement: [Drums and Guns, hasTrack, Dust on the Window]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dust on the Window
Context triple: [Drums and Guns, hasTrack, Dust on the Window]
  • A. Breath on a Window
    "Breath on a Window" is a song by American rock band Alice in Chains from their 2013 album *The Devil Put Dinosaurs Here*.
  • B. Through the Window
    "Through the Window" is a song featured on Eddie Vedder’s acoustic solo album "Higher Truth."
  • C. Through a Window
    Through a Window is a book by primatologist Jane Goodall that reflects on her decades of research and personal experiences with chimpanzees in the wild.
  • D. The Light Behind the Window
    The Light Behind the Window is a historical fiction novel by Lucinda Riley that intertwines past and present through a family mystery set partly in wartime France.
  • E. At My Window
    "At My Window" is a song by the American rock band Sunflower.
  • 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: Dust on the Window
Triple: [Drums and Guns, hasTrack, Dust on the Window]
Generated description
"Dust on the Window" is a song by the American indie rock band Low from their album "Drums and Guns," known for its sparse, haunting sound and introspective mood.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dust on the Window
Target entity description: "Dust on the Window" is a song by the American indie rock band Low from their album "Drums and Guns," known for its sparse, haunting sound and introspective mood.
  • A. Breath on a Window
    "Breath on a Window" is a song by American rock band Alice in Chains from their 2013 album *The Devil Put Dinosaurs Here*.
  • B. Through the Window
    "Through the Window" is a song featured on Eddie Vedder’s acoustic solo album "Higher Truth."
  • C. Through a Window
    Through a Window is a book by primatologist Jane Goodall that reflects on her decades of research and personal experiences with chimpanzees in the wild.
  • D. The Light Behind the Window
    The Light Behind the Window is a historical fiction novel by Lucinda Riley that intertwines past and present through a family mystery set partly in wartime France.
  • E. At My Window
    "At My Window" is a song by the American rock band Sunflower.
  • 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42d962b988190bdbba81ac63c7e6e completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fce16688190976d3760898ca5d8 completed May 11, 2026, 4:49 a.m.
NEDg Description generation batch_6a01607ee0c881909acd5f0f741e5e15 completed May 11, 2026, 4:52 a.m.
NED2 Entity disambiguation (via description) batch_6a016158b1d081909b62cf73e14b3e78 completed May 11, 2026, 4:55 a.m.
Created at: April 10, 2026, 5:37 a.m.