Triple

T16382980
Position Surface form Disambiguated ID Type / Status
Subject Steve Howe E397853 entity
Predicate notableWork P4 FINISHED
Object Fragile E430613 NE FINISHED

How this triple was built (2 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: Fragile | Statement: [Steve Howe, notableWork, Fragile]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fragile
Context triple: [Steve Howe, notableWork, Fragile]
  • A. Fragile
    "Fragile" is a 1971 progressive rock album by the band Yes, featuring Jon Anderson as lead vocalist and known for its complex compositions and iconic cover art.
  • B. Fragile chosen
    "Fragile" is a 1985 song by English musician Sting, known for its gentle acoustic style and reflective lyrics on the themes of violence and human vulnerability.
  • C. Fragile
    Fragile is a women's fragrance by Jean Paul Gaultier known for its distinctive floral notes and iconic, snow-globe-inspired bottle design.
  • D. Fragile Things
    Fragile Things is a collection of short stories and poems by Neil Gaiman that blends fantasy, horror, and mythic themes in his signature darkly imaginative style.
  • E. Fragile Beauty
    Fragile Beauty is a photographic exhibition by Prince Hussain Aga Khan that showcases the delicate splendor and vulnerability of marine and wildlife environments.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319ddcef08190a2081855b5cf6762 completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00356b00408190beab51a23011be67 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.