Triple

T14409504
Position Surface form Disambiguated ID Type / Status
Subject Savage Mode E357286 entity
Predicate hasTrack P3284 FINISHED
Object Mad High
"Mad High" is a track by 21 Savage and Metro Boomin from their collaborative trap album *Savage Mode*.
E1097071 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: Mad High | Statement: [Savage Mode, hasTrack, Mad High]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mad High
Context triple: [Savage Mode, hasTrack, Mad High]
  • A. So High School
    "So High School" is a song by Taylor Swift from her album "The Tortured Poets Department."
  • B. Down High School
    Down High School is a co-educational grammar school in Downpatrick, Northern Ireland, known for its strong academic performance and long-established history in the region.
  • C. Sugarhigh
    "Sugarhigh" is a high-energy rock song best known for its climactic performance scene in the 1995 cult film *Empire Records*.
  • D. Sky High
    Sky High is a 2005 family-friendly superhero comedy film about a high school for teenage heroes, starring Kurt Russell.
  • E. Big School
    Big School is a British television sitcom starring Frances de la Tour, set in a dysfunctional secondary school and centered on the comedic antics of its staff and students.
  • 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: Mad High
Triple: [Savage Mode, hasTrack, Mad High]
Generated description
"Mad High" is a track by 21 Savage and Metro Boomin from their collaborative trap album *Savage Mode*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mad High
Target entity description: "Mad High" is a track by 21 Savage and Metro Boomin from their collaborative trap album *Savage Mode*.
  • A. So High School
    "So High School" is a song by Taylor Swift from her album "The Tortured Poets Department."
  • B. Down High School
    Down High School is a co-educational grammar school in Downpatrick, Northern Ireland, known for its strong academic performance and long-established history in the region.
  • C. Sugarhigh
    "Sugarhigh" is a high-energy rock song best known for its climactic performance scene in the 1995 cult film *Empire Records*.
  • D. Sky High
    Sky High is a 2005 family-friendly superhero comedy film about a high school for teenage heroes, starring Kurt Russell.
  • E. Big School
    Big School is a British television sitcom starring Frances de la Tour, set in a dysfunctional secondary school and centered on the comedic antics of its staff and students.
  • 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90c9b3448190aec1608836a5e913 completed April 14, 2026, 7:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5524e26c81909424b5ba88b5f330 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd56844d7c8190906b6550fb1c28d5 completed May 8, 2026, 3:20 a.m.
NED2 Entity disambiguation (via description) batch_69fd5731c9188190bda2958bef87dfe2 completed May 8, 2026, 3:23 a.m.
Created at: April 10, 2026, 1:17 a.m.