Triple

T394381
Position Surface form Disambiguated ID Type / Status
Subject Miguel E8949 entity
Predicate notableSong P4 FINISHED
Object Coffee
"Coffee" is a song by the American singer-songwriter Miguel, known for its smooth blend of R&B and sensual, atmospheric production.
E49777 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: Coffee | Statement: [Miguel, notableSong, Coffee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coffee
Context triple: [Miguel, notableSong, Coffee]
  • A. Blue Mountains coffee
    Blue Mountains coffee is a highly prized Jamaican coffee variety renowned for its mild flavor, smooth body, and low bitterness, grown at high elevations in the Blue Mountains region.
  • B. Mocha
    Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
  • C. Cocoa
    Cocoa is Apple’s native object-oriented application framework for building graphical user interfaces and other software on macOS.
  • D. The Bean
    The Bean is a famous stainless steel public sculpture by artist Anish Kapoor located in Chicago’s Millennium Park, renowned for its highly polished, reflective surface and iconic, bean-like shape.
  • E. COFHE
    COFHE is a consortium of highly selective private colleges and universities in the United States that collaborates on issues of financial aid, admissions, and institutional research.
  • 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: Coffee
Triple: [Miguel, notableSong, Coffee]
Generated description
"Coffee" is a song by the American singer-songwriter Miguel, known for its smooth blend of R&B and sensual, atmospheric production.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Coffee
Target entity description: "Coffee" is a song by the American singer-songwriter Miguel, known for its smooth blend of R&B and sensual, atmospheric production.
  • A. Blue Mountains coffee
    Blue Mountains coffee is a highly prized Jamaican coffee variety renowned for its mild flavor, smooth body, and low bitterness, grown at high elevations in the Blue Mountains region.
  • B. Mocha
    Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
  • C. Cocoa
    Cocoa is Apple’s native object-oriented application framework for building graphical user interfaces and other software on macOS.
  • D. The Bean
    The Bean is a famous stainless steel public sculpture by artist Anish Kapoor located in Chicago’s Millennium Park, renowned for its highly polished, reflective surface and iconic, bean-like shape.
  • E. COFHE
    COFHE is a consortium of highly selective private colleges and universities in the United States that collaborates on issues of financial aid, admissions, and institutional research.
  • 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_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec77a8a08190b6f96373aa8c1346 completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a405fa43448190b3e78d83e791b105 completed March 1, 2026, 9:25 a.m.
NEDg Description generation batch_69a4070f76308190bd898dcdb27f3277 completed March 1, 2026, 9:29 a.m.
NED2 Entity disambiguation (via description) batch_69a40794523081908839f90446beba83 completed March 1, 2026, 9:32 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.