Triple

T14327532
Position Surface form Disambiguated ID Type / Status
Subject Heather Nova E355251 entity
Predicate notableWork P4 FINISHED
Object Glow Stars
Glow Stars is the 1993 debut studio album by Bermudian singer-songwriter Heather Nova, blending ethereal vocals with atmospheric, alternative rock and folk influences.
E1094247 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: Glow Stars | Statement: [Heather Nova, notableWork, Glow Stars]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glow Stars
Context triple: [Heather Nova, notableWork, Glow Stars]
  • A. Glow
    "Glow" is a song featured on Kelly Clarkson's holiday album "When Christmas Comes Around..." that showcases her soulful vocals in a festive, contemporary pop setting.
  • B. Glow
    "Glow" is a track by the artist Tasty, likely featuring an energetic, electronic-influenced sound characteristic of their music style.
  • C. Glow
    "Glow" is a pop song by Australian singer Jessica Mauboy, showcasing her soulful vocals and contemporary R&B-influenced style.
  • D. Glow
    Glow is a track from Drake’s playlist-style album "More Life," known for its mellow production and guest appearance by Kanye West.
  • E. Glow
    Glow is a generative flow-based model architecture used for high-quality image and audio synthesis through invertible transformations.
  • 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: Glow Stars
Triple: [Heather Nova, notableWork, Glow Stars]
Generated description
Glow Stars is the 1993 debut studio album by Bermudian singer-songwriter Heather Nova, blending ethereal vocals with atmospheric, alternative rock and folk influences.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Glow Stars
Target entity description: Glow Stars is the 1993 debut studio album by Bermudian singer-songwriter Heather Nova, blending ethereal vocals with atmospheric, alternative rock and folk influences.
  • A. Glow
    "Glow" is a song featured on Kelly Clarkson's holiday album "When Christmas Comes Around..." that showcases her soulful vocals in a festive, contemporary pop setting.
  • B. Glow
    "Glow" is a track by the artist Tasty, likely featuring an energetic, electronic-influenced sound characteristic of their music style.
  • C. Glow
    "Glow" is a pop song by Australian singer Jessica Mauboy, showcasing her soulful vocals and contemporary R&B-influenced style.
  • D. Glow
    Glow is a track from Drake’s playlist-style album "More Life," known for its mellow production and guest appearance by Kanye West.
  • E. Glow
    Glow is a generative flow-based model architecture used for high-quality image and audio synthesis through invertible transformations.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1c3e70819084b6728ac5c18561 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd46927af48190b91095d852fcacbe completed May 8, 2026, 2:12 a.m.
NEDg Description generation batch_69fd47fa764c8190b1d691f5847b7a05 completed May 8, 2026, 2:18 a.m.
NED2 Entity disambiguation (via description) batch_69fd492226888190a014b23e506ab19c completed May 8, 2026, 2:23 a.m.
Created at: April 10, 2026, 1:13 a.m.