Triple

T23081542
Position Surface form Disambiguated ID Type / Status
Subject Confessin’ the Blues E575486 entity
Predicate hasNotableCover P20178 FINISHED
Object Taj Mahal 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: Taj Mahal | Statement: [Confessin’ the Blues, hasNotableCover, Taj Mahal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taj Mahal
Context triple: [Confessin’ the Blues, hasNotableCover, Taj Mahal]
  • A. Taj Mahal
    The Taj Mahal is a 17th-century white marble mausoleum in Agra, India, renowned worldwide as a masterpiece of Mughal architecture and a symbol of enduring love.
  • B. Taj Mahal chosen
    Taj Mahal is an American blues musician and singer-songwriter known for blending traditional blues with elements of world music, including Caribbean, African, and Hawaiian influences.
  • C. Taj
    Taj was the former name of Esteghlal F.C., one of Iran’s most successful and popular football clubs.
  • D. Taj
    Taj is the stage name of Tamara Johnson, an American R&B singer best known as a member of the girl group SWV (Sisters With Voices).
  • E. Taj
    Taj is an American actor and musician best known as the son of Aerosmith frontman Steven Tyler.
  • 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_69e245be28d48190ad1348d5a73db37d completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c67e06881908d24d6267bb49553 completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.