Triple

T16435779
Position Surface form Disambiguated ID Type / Status
Subject William Morris Agency E399175 entity
Predicate notableClient P7186 FINISHED
Object Adele E39853 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: Adele | Statement: [William Morris Agency, notableClient, Adele]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adele
Context triple: [William Morris Agency, notableClient, Adele]
  • A. Adele chosen
    Adele is a British singer-songwriter renowned for her powerful soulful voice and emotionally resonant hits such as "Rolling in the Deep" and "Hello."
  • B. Adele
    Adele is a witty and vivacious chambermaid who provides much of the comic relief in Johann Strauss II’s operetta "Die Fledermaus."
  • C. Adele
    Adele is the middle name of Florence Adele Vanderbilt Twombly, a prominent American socialite and member of the wealthy Vanderbilt family during the Gilded Age.
  • D. Adele Casagrande
    Adele Casagrande was an Italian fashion designer and entrepreneur best known as the co-founder of the luxury fashion house Fendi.
  • E. Adele Georgiana Gianopoulos
    Adele Georgiana Gianopoulos is the daughter of American actress and author Molly Ringwald.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba224988190b7cccc42f35e54de completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0045893c5481909e5ffa9460dc5b3d completed May 10, 2026, 8:44 a.m.
Created at: April 10, 2026, 5:10 a.m.