Triple

T13893203
Position Surface form Disambiguated ID Type / Status
Subject Into the Groove E334023 entity
Predicate bSideOf P15273 FINISHED
Object Angel
"Angel" is a 1984 pop song by Madonna, released as a single from her album "Like a Virgin."
 E1067587 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: Angel | Statement: [Into the Groove, bSideOf, Angel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Angel
Context triple: [Into the Groove, bSideOf, Angel]
  • A. Angel
    "Angel" is a 1937 romantic comedy film directed by Ernst Lubitsch, known for its sophisticated wit and starring Marlene Dietrich, Herbert Marshall, and Melvyn Douglas.
  • B. Angel
    An angel is a spiritual being found in various religious traditions, typically depicted as a messenger or servant of the divine.
  • C. Angel
    Angel is a winged mutant warrior in the X-Men universe, often depicted with metallic feathered wings and a conflicted, tormented nature.
  • D. Angel
    Angel is a character in William Wordsworth's autobiographical poem "The Prelude," symbolizing spiritual guidance and inspiration in the poet's inner and artistic development.
  • E. Angel
    "Angel" is a dark, trip hop song by Massive Attack, known for its brooding atmosphere, slow-building intensity, and prominent use in film and television soundtracks.
  • 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: Angel
Triple: [Into the Groove, bSideOf, Angel]
Generated description
"Angel" is a 1984 pop song by Madonna, released as a single from her album "Like a Virgin."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Angel
Target entity description: "Angel" is a 1984 pop song by Madonna, released as a single from her album "Like a Virgin."
  • A. Angel
    "Angel" is a song by the American rock band Aerosmith, best known as a power ballad from their 1987 album *Permanent Vacation*.
  • B. Angel
    "Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
  • C. Angel
    "Angel" is a melancholic, piano-driven ballad by Canadian singer-songwriter Sarah McLachlan, widely known for its emotional resonance and use in various charitable and memorial contexts.
  • D. Angel
    "Angel" is a dark, trip hop song by Massive Attack, known for its brooding atmosphere, slow-building intensity, and prominent use in film and television soundtracks.
  • E. Angel
    "Angel" is a 1937 romantic comedy film directed by Ernst Lubitsch, known for its sophisticated wit and starring Marlene Dietrich, Herbert Marshall, and Melvyn Douglas.
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de23a537d4819093c2bae2a244816a completed April 14, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c71ca8a881908ac02687fbfe62fb completed May 3, 2026, 10:07 p.m.
NEDg Description generation batch_69f7c7e1247481908073c1e282c3619f completed May 3, 2026, 10:10 p.m.
NED2 Entity disambiguation (via description) batch_69f7c8f2b5588190b6143d676eb648a0 completed May 3, 2026, 10:15 p.m.
Created at: April 9, 2026, 10:15 p.m.