Triple

T10526699
Position Surface form Disambiguated ID Type / Status
Subject The Pointer Sisters E248323 entity
Predicate notableWork P4 FINISHED
Object "Fire"
"Fire" is a 1978 hit R&B/pop song by The Pointer Sisters, written by Bruce Springsteen and known for its sultry vocals and chart success.
 E869444 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: "Fire" | Statement: [The Pointer Sisters, notableWork, "Fire"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: "Fire"
Context triple: [The Pointer Sisters, notableWork, "Fire"]
  • A. "Burn"
    "Burn" is an R&B ballad best known as one of Usher's major hits from his 2004 album "Confessions," co-written and produced by Jermaine Dupri.
  • B. Feed the Fire
    Feed the Fire is a song by the American punk rock band Passwords.
  • C. On Fire
    On Fire is a nonfiction book by Naomi Klein that explores the climate crisis and advocates for transformative, justice-centered solutions such as a Green New Deal.
  • D. On Fire
    "On Fire" is an ancient treatise by the Greek philosopher Theophrastus that examines the nature, causes, and properties of fire within early scientific and philosophical thought.
  • E. On Fire
    "On Fire" is a hip-hop track produced by Kasseem Daoud Dean, better known as Swizz Beatz, showcasing his signature energetic, hard-hitting production style.
  • 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: "Fire"
Triple: [The Pointer Sisters, notableWork, "Fire"]
Generated description
"Fire" is a 1978 hit R&B/pop song by The Pointer Sisters, written by Bruce Springsteen and known for its sultry vocals and chart success.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: "Fire"
Target entity description: "Fire" is a 1978 hit R&B/pop song by The Pointer Sisters, written by Bruce Springsteen and known for its sultry vocals and chart success.
  • A. "Burn"
    "Burn" is an R&B ballad best known as one of Usher's major hits from his 2004 album "Confessions," co-written and produced by Jermaine Dupri.
  • B. Feed the Fire
    Feed the Fire is a song by the American punk rock band Passwords.
  • C. On Fire
    On Fire is a nonfiction book by Naomi Klein that explores the climate crisis and advocates for transformative, justice-centered solutions such as a Green New Deal.
  • D. On Fire
    "On Fire" is an ancient treatise by the Greek philosopher Theophrastus that examines the nature, causes, and properties of fire within early scientific and philosophical thought.
  • E. On Fire
    "On Fire" is a hip-hop track produced by Kasseem Daoud Dean, better known as Swizz Beatz, showcasing his signature energetic, hard-hitting production style.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509f5ec348190875c8c877e70ba4a completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e31350c8190a7493cdc33cc450a completed April 10, 2026, 2:50 p.m.
NEDg Description generation batch_69d9107e8b94819086ebba1675a0db54 completed April 10, 2026, 3 p.m.
NED2 Entity disambiguation (via description) batch_69d911a16b1481909197b00c30de48c4 completed April 10, 2026, 3:05 p.m.
Created at: April 6, 2026, 12:29 p.m.