Triple

T22948774
Position Surface form Disambiguated ID Type / Status
Subject Underdog E569947 entity
Predicate writer P1360 FINISHED
Object Ed Sheeran NE NERFINISHED

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: Ed Sheeran | Statement: [Underdog, writer, Ed Sheeran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Sheeran
Context triple: [Underdog, writer, Ed Sheeran]
  • A. Ed Sheeran chosen
    Ed Sheeran is an English singer-songwriter and musician known for his melodic pop hits, acoustic ballads, and global commercial success.
  • B. Sam Smith
    Sam Smith is an English singer-songwriter known for their soulful pop ballads and powerful vocals, with multiple Grammy and Brit Awards to their name.
  • C. George Ezra
    George Ezra is an English singer-songwriter known for his deep, soulful voice and hit songs like "Budapest" and "Shotgun."
  • D. Lewis Capaldi
    Lewis Capaldi is a Scottish singer-songwriter known for his powerful, emotive ballads and global hit "Someone You Loved."
  • E. Harry Styles
    Harry Styles is a British singer, songwriter, and actor who rose to fame with One Direction before launching a successful solo career known for its genre-blending pop and rock and distinctive fashion style.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2459199d08190a8184ee2aa935842 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1819fbf8c8190ad80c93f1507aa73 completed April 29, 2026, 3:57 a.m.
Created at: April 17, 2026, 3:46 p.m.