Triple

T19206608
Position Surface form Disambiguated ID Type / Status
Subject Ruth Morse E480249 entity
Predicate familyName P18 FINISHED
Object Morse 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: Morse | Statement: [Ruth Morse, familyName, Morse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Morse
Context triple: [Ruth Morse, familyName, Morse]
  • A. Morse
    Morse is the middle name of Mary Baker Eddy, the founder of Christian Science.
  • B. Morse chosen
    Morse is a surname most famously associated with Samuel Morse, the American inventor and co-developer of the Morse code communication system.
  • C. Morse code
    Morse code is a system of encoding text characters as sequences of short and long signals (dots and dashes) used historically for long-distance telegraph and radio communication.
  • D. Morse Signal Devices
    Morse Signal Devices was a company associated with A. Reynolds Morse, likely involved in the development or manufacture of signaling or communication equipment.
  • E. Télégraphe
    Télégraphe is a Paris Métro station in the 20th arrondissement, named after the nearby historical telegraph tower site.
  • 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_69d8e8cb8c348190b52075823911c869 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5f99d8ad0819098ebd4ee007149f1 completed April 20, 2026, 10:02 a.m.
Created at: April 10, 2026, 1:19 p.m.