Triple

T14045747
Position Surface form Disambiguated ID Type / Status
Subject High as Hope E337950 entity
Predicate single P3283 FINISHED
Object Hunger
"Hunger" is a song by English indie pop band Florence and the Machine, featured on their 2018 album *High as Hope*.
 E337935 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: Hunger | Statement: [High as Hope, single, Hunger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hunger
Context triple: [High as Hope, single, Hunger]
  • A. Hunger
    Hunger is a seminal 1890 novel by Norwegian author Knut Hamsun that follows a starving writer’s psychological descent and is considered an early landmark of modernist literature.
  • B. Hunger
    Hunger is a 2008 historical drama film directed by Steve McQueen that portrays the 1981 Irish hunger strike led by Bobby Sands in Northern Ireland’s Maze Prison.
  • C. Hunger
    "Hunger" is a short story collection by American author Lan Samantha Chang that explores themes of family, immigration, and cultural identity.
  • D. Hunger
    "Hunger" is a hip-hop track by rapper Hodgy Beats that showcases his introspective lyrics and distinctive, off-kilter style.
  • E. Hunger
    Hunger is a 2014 Nigerian drama film directed by Seyi Babatope that explores themes of ambition, desperation, and moral compromise in contemporary Lagos.
  • 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: Hunger
Triple: [High as Hope, single, Hunger]
Generated description
"Hunger" is a song by English indie pop band Florence and the Machine, featured on their 2018 album *High as Hope*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hunger
Target entity description: "Hunger" is a song by English indie pop band Florence and the Machine, featured on their 2018 album *High as Hope*.
  • A. Hunger chosen
    "Hunger" is a 2018 song by English indie rock band Florence and the Machine that explores themes of longing, vulnerability, and self-destructive desire.
  • B. Hunger
    "Hunger" is a hip-hop track by rapper Hodgy Beats that showcases his introspective lyrics and distinctive, off-kilter style.
  • C. Hunger
    Hunger is a 2008 historical drama film directed by Steve McQueen that portrays the 1981 Irish hunger strike led by Bobby Sands in Northern Ireland’s Maze Prison.
  • D. Hunger
    Hunger is a 2014 Nigerian drama film directed by Seyi Babatope that explores themes of ambition, desperation, and moral compromise in contemporary Lagos.
  • E. Hunger
    "Hunger" is a short story collection by American author Lan Samantha Chang that explores themes of family, immigration, and cultural identity.
  • F. None of above.

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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de312df37081909f45ce3e219af5dc completed April 14, 2026, 12:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb65c1a90819097754497f07f5312 completed May 7, 2026, 3:57 p.m.
NEDg Description generation batch_69fcc54039f081908c397005fc4e4e9b completed May 7, 2026, 5 p.m.
NED2 Entity disambiguation (via description) batch_69fcc61353d481908192a1e2f44e6a94 completed May 7, 2026, 5:04 p.m.
Created at: April 9, 2026, 10:20 p.m.