Triple

T22545144
Position Surface form Disambiguated ID Type / Status
Subject Julia Prinsep Jackson E557399 entity
Predicate sibling P363 FINISHED
Object Maria Pattle 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: Maria Pattle | Statement: [Julia Prinsep Jackson, sibling, Maria Pattle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria Pattle
Context triple: [Julia Prinsep Jackson, sibling, Maria Pattle]
  • A. Virginia Pattle chosen
    Virginia Pattle was a 19th-century member of the prominent Pattle family, known within Victorian high society and connected to notable artistic and literary figures.
  • B. Mary Pugh
    Mary Pugh is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Pugh.
  • C. Mary Elcho
    Mary Elcho was a prominent British aristocrat and socialite of the late 19th century, best known as a leading member of the intellectual and artistic circle known as "The Souls."
  • D. Marian Pugh
    Marian Pugh is best known as the spouse of prominent Australian painter Clifton Pugh.
  • E. Patricia Liddell
    Patricia Liddell is the daughter of Australian wireless pioneer and radio engineer Florence Violet McKenzie.
  • 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_69e11e58662081909ae346ab384514ca completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f34a0688190ad55be067db8e21b completed April 29, 2026, 1:30 a.m.
Created at: April 16, 2026, 8:51 p.m.