Triple

T19982595
Position Surface form Disambiguated ID Type / Status
Subject Mrs. Ferrars E493853 entity
Predicate hasFamilyName P18 FINISHED
Object Ferrars 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: Ferrars | Statement: [Mrs. Ferrars, hasFamilyName, Ferrars]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferrars
Context triple: [Mrs. Ferrars, hasFamilyName, Ferrars]
  • A. Ferrars chosen
    Ferrars is the surname of Edward Ferrars, a central character in Jane Austen's novel "Sense and Sensibility."
  • B. Fitzwilliam
    Fitzwilliam is an Anglo-Irish aristocratic surname historically associated with prominent landowning and political families in Britain and Ireland.
  • C. Fitzwilliam
    Fitzwilliam is a former coal mining village in West Yorkshire, England, known for its industrial heritage and subsequent regeneration efforts.
  • D. Stanhope
    Stanhope is a small rural town in northern Victoria, Australia, known for its dairy farming and agricultural community.
  • E. Stanhope
    Stanhope is an English surname historically associated with several notable figures in British politics, literature, and the aristocracy.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d14c3c08190b1ba8f4da08a4ccf completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.