Triple

T1864837
Position Surface form Disambiguated ID Type / Status
Subject Two Eleven E34895 entity
Predicate hasPart P35 FINISHED
Object So Sick
"So Sick" is a popular R&B song by Ne-Yo, known for its melancholic theme of heartbreak and its success as one of his breakthrough hits.
E208298 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: So Sick | Statement: [Two Eleven, hasPart, So Sick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: So Sick
Context triple: [Two Eleven, hasPart, So Sick]
  • A. Love Sick
    "Love Sick" is a song by Bob Dylan, best known as the haunting, blues-infused opening track of his 1997 album *Time Out of Mind*.
  • B. You Are All Diseased
    You Are All Diseased is a 1999 stand-up comedy special and album by George Carlin known for its dark, incisive social and political commentary.
  • C. Sick To My Stomach
    "Sick To My Stomach" is a song by American singer Rebecca Black, known for its emotionally charged lyrics and pop production.
  • D. Love Is My Disease
    "Love Is My Disease" is a song by Alicia Keys from her 2009 R&B/soul album *The Element of Freedom*.
  • E. Sicko Mode
    "Sicko Mode" is a multi-part, genre-blending hip-hop track by Travis Scott featuring Drake that became a major commercial and cultural hit.
  • 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: So Sick
Triple: [Two Eleven, hasPart, So Sick]
Generated description
"So Sick" is a popular R&B song by Ne-Yo, known for its melancholic theme of heartbreak and its success as one of his breakthrough hits.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: So Sick
Target entity description: "So Sick" is a popular R&B song by Ne-Yo, known for its melancholic theme of heartbreak and its success as one of his breakthrough hits.
  • A. Love Sick
    "Love Sick" is a song by Bob Dylan, best known as the haunting, blues-infused opening track of his 1997 album *Time Out of Mind*.
  • B. You Are All Diseased
    You Are All Diseased is a 1999 stand-up comedy special and album by George Carlin known for its dark, incisive social and political commentary.
  • C. Sick To My Stomach
    "Sick To My Stomach" is a song by American singer Rebecca Black, known for its emotionally charged lyrics and pop production.
  • D. Love Is My Disease
    "Love Is My Disease" is a song by Alicia Keys from her 2009 R&B/soul album *The Element of Freedom*.
  • E. Sicko Mode
    "Sicko Mode" is a multi-part, genre-blending hip-hop track by Travis Scott featuring Drake that became a major commercial and cultural hit.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb0a208e481908406c008f700a585 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1d540c0819099558507bdf2ffa4 completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add2c4943c81909ff3163330aa4f80 completed March 8, 2026, 7:49 p.m.
NED2 Entity disambiguation (via description) batch_69add38c2b3c8190b0f33bc36d475a63 completed March 8, 2026, 7:52 p.m.
Created at: March 4, 2026, 7:34 p.m.