Triple

T20693140
Position Surface form Disambiguated ID Type / Status
Subject 4′33″ E508599 entity
Predicate publisher P29 FINISHED
Object Edition Peters
Edition Peters is a renowned classical music publishing house known for issuing scores by major composers and contemporary avant-garde works.
E1445458 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: Edition Peters | Statement: [4′33″, publisher, Edition Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edition Peters
Context triple: [4′33″, publisher, Edition Peters]
  • A. Piatkus
    Piatkus is a UK-based publishing imprint known for its commercial fiction and non-fiction titles, particularly in romance, crime, and personal development.
  • B. Bernard & Graefe
    Bernard & Graefe is a German publishing house known for its specialized works on military history and related non-fiction.
  • C. Schiffer
    Schiffer is a German surname borne by various notable individuals in fields such as modeling, politics, and academia.
  • D. Faber
    Faber is a retired English professor in Ray Bradbury’s dystopian novel "Fahrenheit 451" who secretly mentors the protagonist and represents the value of literature and critical thought in a censored society.
  • E. Faber
    Faber is a surname most notably associated with Sandra Faber, an influential American astronomer and cosmologist.
  • 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: Edition Peters
Triple: [4′33″, publisher, Edition Peters]
Generated description
Edition Peters is a renowned classical music publishing house known for issuing scores by major composers and contemporary avant-garde works.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Edition Peters
Target entity description: Edition Peters is a renowned classical music publishing house known for issuing scores by major composers and contemporary avant-garde works.
  • A. Piatkus
    Piatkus is a UK-based publishing imprint known for its commercial fiction and non-fiction titles, particularly in romance, crime, and personal development.
  • B. Bernard & Graefe
    Bernard & Graefe is a German publishing house known for its specialized works on military history and related non-fiction.
  • C. Schiffer
    Schiffer is a German surname borne by various notable individuals in fields such as modeling, politics, and academia.
  • D. Faber
    Faber is a retired English professor in Ray Bradbury’s dystopian novel "Fahrenheit 451" who secretly mentors the protagonist and represents the value of literature and critical thought in a censored society.
  • E. Faber
    Faber is a surname most notably associated with Sandra Faber, an influential American astronomer and cosmologist.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c10fc4088190ab71ef078600954b completed April 21, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7e43a3c81909f63e63e30e9c435 completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d91216bc8190909e0e37f6d5e612 completed May 16, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_6a08d99214b48190b0ffba4026d3fa39 completed May 16, 2026, 8:54 p.m.
Created at: April 16, 2026, 12:09 p.m.