Triple

T13481169
Position Surface form Disambiguated ID Type / Status
Subject Donnie Darko E318373 entity
Predicate notableSong P4 FINISHED
Object Mad World
"Mad World" is a melancholic song originally by Tears for Fears, widely popularized by Gary Jules’ haunting cover used in the film *Donnie Darko*.
 E1043048 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 World | Statement: [Donnie Darko, notableSong, Mad World]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mad World
Context triple: [Donnie Darko, notableSong, Mad World]
  • A. Mad World
    "Mad World" is a popular electronic dance track by Australian DJ and producer Timmy Trumpet, known for its energetic festival sound and catchy melodic hooks.
  • B. A Long and Sad Goodbye
    "A Long and Sad Goodbye" is a melancholic rock ballad by Lenny Kravitz featured on his 2008 album *It Is Time for a Love Revolution*.
  • C. Dreamland
    Dreamland is a song by Joni Mitchell featured on her 1977 album "Don Juan's Reckless Daughter."
  • D. Dreamland
    Dreamland is a psychedelic, synth-driven pop album by British band Glass Animals that explores nostalgic memories and personal storytelling.
  • E. Dreamland
    Dreamland is a jazz-influenced vocal album by Madeleine Peyroux that introduced her distinctive, Billie Holiday–evoking style to a wider audience.
  • 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 World
Triple: [Donnie Darko, notableSong, Mad World]
Generated description
"Mad World" is a melancholic song originally by Tears for Fears, widely popularized by Gary Jules’ haunting cover used in the film *Donnie Darko*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mad World
Target entity description: "Mad World" is a melancholic song originally by Tears for Fears, widely popularized by Gary Jules’ haunting cover used in the film *Donnie Darko*.
  • A. Mad World
    "Mad World" is a popular electronic dance track by Australian DJ and producer Timmy Trumpet, known for its energetic festival sound and catchy melodic hooks.
  • B. A Long and Sad Goodbye
    "A Long and Sad Goodbye" is a melancholic rock ballad by Lenny Kravitz featured on his 2008 album *It Is Time for a Love Revolution*.
  • C. Dreamland
    Dreamland is a song by Joni Mitchell featured on her 1977 album "Don Juan's Reckless Daughter."
  • D. Dreamland
    Dreamland is a jazz-influenced vocal album by Madeleine Peyroux that introduced her distinctive, Billie Holiday–evoking style to a wider audience.
  • E. Dreamland
    "Dreamland" is a synth-pop single by the Pet Shop Boys featuring Years & Years, known for its nostalgic yet contemporary electronic sound.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf36c6b08190ba99400600e0b662 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f74635145c8190a42199fe4ed8c2a5 completed May 3, 2026, 12:57 p.m.
NEDg Description generation batch_69f748dfd4f081908fd5d77fe70f9db4 completed May 3, 2026, 1:08 p.m.
NED2 Entity disambiguation (via description) batch_69f74965c53081909c662f7f991849bf completed May 3, 2026, 1:11 p.m.
Created at: April 9, 2026, 9:42 p.m.