Triple

T15761238
Position Surface form Disambiguated ID Type / Status
Subject Too Good at Goodbyes E382100 entity
Predicate nextSingle P25313 FINISHED
Object Pray
"Pray" is a soulful pop ballad by English singer Sam Smith that reflects on themes of guilt, faith, and seeking redemption.
 E1175239 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: Pray | Statement: [Too Good at Goodbyes, nextSingle, Pray]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pray
Context triple: [Too Good at Goodbyes, nextSingle, Pray]
  • A. Pray
    "Pray" is a hit pop ballad by British boy band Take That, released in 1993 and known for becoming one of their early chart-topping singles.
  • B. Pray
    "Pray" is a 1990 hit single by MC Hammer that blends hip-hop with prominent sampling of Prince's "When Doves Cry" and became one of his most commercially successful songs.
  • C. Prayer
    "Prayer" is a soulful, politically charged track by D'Angelo and The Vanguard from the critically acclaimed album *Black Messiah*.
  • D. Prayer
    "Prayer" is a song by the American rock band Disturbed, known for its heavy riffs and introspective lyrics that reflect themes of struggle and resilience.
  • E. Praying
    "Praying" is a powerful piano ballad by Kesha that marks her emotional comeback, addressing themes of trauma, forgiveness, and resilience.
  • 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: Pray
Triple: [Too Good at Goodbyes, nextSingle, Pray]
Generated description
"Pray" is a soulful pop ballad by English singer Sam Smith that reflects on themes of guilt, faith, and seeking redemption.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pray
Target entity description: "Pray" is a soulful pop ballad by English singer Sam Smith that reflects on themes of guilt, faith, and seeking redemption.
  • A. Pray
    "Pray" is a hit pop ballad by British boy band Take That, released in 1993 and known for becoming one of their early chart-topping singles.
  • B. Pray
    "Pray" is a 1990 hit single by MC Hammer that blends hip-hop with prominent sampling of Prince's "When Doves Cry" and became one of his most commercially successful songs.
  • C. Prayer
    "Prayer" is a song by the American rock band Disturbed, known for its heavy riffs and introspective lyrics that reflect themes of struggle and resilience.
  • D. Prayer
    "Prayer" is a soulful, politically charged track by D'Angelo and The Vanguard from the critically acclaimed album *Black Messiah*.
  • E. Praying
    "Praying" is a powerful piano ballad by Kesha that marks her emotional comeback, addressing themes of trauma, forgiveness, and resilience.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b52c548190a0ffa4493a4eb15c completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8774eda08190a6231b4fd5027e6f completed May 9, 2026, 7:13 p.m.
NEDg Description generation batch_69ff885d33708190adb157afa7dc2e07 completed May 9, 2026, 7:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff8948cc68819085c3953226236394 completed May 9, 2026, 7:21 p.m.
Created at: April 10, 2026, 4:47 a.m.