Triple

T18967452
Position Surface form Disambiguated ID Type / Status
Subject Ultravox E464077 entity
Predicate notableWork P4 FINISHED
Object Hymn
"Hymn" is a 1982 synth-pop song by British band Ultravox, known for its anthemic melody and themes of faith and corruption.
E1352636 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: Hymn | Statement: [Ultravox, notableWork, Hymn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hymn
Context triple: [Ultravox, notableWork, Hymn]
  • A. Hymn
    "Hymn" is a 2018 classical crossover and symphonic album by soprano Sarah Brightman that blends inspirational themes with orchestral and choral arrangements.
  • B. Hymns
    Hymns is a collection of learned, stylistically refined religious poems by the Hellenistic poet Callimachus that rework traditional Greek myth and cult in an innovative, Alexandrian manner.
  • C. Hymns
    Hymns is the fifth studio album by British indie rock band Bloc Party, marking a stylistic shift toward more spiritual themes and electronic-influenced sounds.
  • D. Hymnen
    Hymnen is a large-scale electronic composition by Karlheinz Stockhausen that weaves together and transforms national anthems into an experimental, multi-channel sound collage.
  • E. HYMS
    HYMS is a UK medical school jointly run by the University of Hull and the University of York, offering undergraduate and postgraduate medical education and research.
  • 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: Hymn
Triple: [Ultravox, notableWork, Hymn]
Generated description
"Hymn" is a 1982 synth-pop song by British band Ultravox, known for its anthemic melody and themes of faith and corruption.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hymn
Target entity description: "Hymn" is a 1982 synth-pop song by British band Ultravox, known for its anthemic melody and themes of faith and corruption.
  • A. Hymn
    "Hymn" is a 2018 classical crossover and symphonic album by soprano Sarah Brightman that blends inspirational themes with orchestral and choral arrangements.
  • B. Hymns
    Hymns is a collection of learned, stylistically refined religious poems by the Hellenistic poet Callimachus that rework traditional Greek myth and cult in an innovative, Alexandrian manner.
  • C. Hymns
    Hymns is the fifth studio album by British indie rock band Bloc Party, marking a stylistic shift toward more spiritual themes and electronic-influenced sounds.
  • D. Hymnen
    Hymnen is a large-scale electronic composition by Karlheinz Stockhausen that weaves together and transforms national anthems into an experimental, multi-channel sound collage.
  • E. HYMS
    HYMS is a UK medical school jointly run by the University of Hull and the University of York, offering undergraduate and postgraduate medical education and research.
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5d7183c8190b1258c0381233efd completed April 20, 2026, 7:29 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05ad37581c8190ac75d3e932e08195 completed May 14, 2026, 11:08 a.m.
NEDg Description generation batch_6a05aeedfd248190a69d128a1ba011e4 completed May 14, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_6a05af7a2c408190b47f2f253bf8c862 completed May 14, 2026, 11:18 a.m.
Created at: April 10, 2026, noon