Triple

T17720954
Position Surface form Disambiguated ID Type / Status
Subject Sarah Louisa Jay E442334 entity
Predicate middleName P143 FINISHED
Object Louisa 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: Louisa | Statement: [Sarah Louisa Jay, middleName, Louisa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louisa
Context triple: [Sarah Louisa Jay, middleName, Louisa]
  • A. Louisa chosen
    Louisa is a feminine given name of Germanic origin, commonly used in English-speaking countries.
  • B. Louisa
    Louisa is a work associated with American actress Ruth Hussey, known for her performances in classic Hollywood cinema.
  • C. Louisa
    Louisa is the middle name of Katharine Louisa Stanley, a 19th-century English writer and member of the prominent Stanley family.
  • D. Louisa
    Louisa is a fictional character from Jean Toomer’s modernist work "Cane," representing themes of love, memory, and the complexities of African American life in the early 20th-century South.
  • E. Louisa
    Louisa is a song by the American indie rock band Lord Huron from their album "Strange Trails."
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4748520a881908dc3446d33236ff7 completed April 19, 2026, 6:21 a.m.
Created at: April 10, 2026, 10:07 a.m.