Triple

T15247473
Position Surface form Disambiguated ID Type / Status
Subject Detective Story Magazine E364421 entity
Predicate featuredAuthor P40446 FINISHED
Object Agnes Christine Johnston E528231 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: Agnes Christine Johnston | Statement: [Detective Story Magazine, featuredAuthor, Agnes Christine Johnston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agnes Christine Johnston
Context triple: [Detective Story Magazine, featuredAuthor, Agnes Christine Johnston]
  • A. Agnes Christine Johnston chosen
    Agnes Christine Johnston was an American screenwriter active during the early to mid-20th century, known for her work on numerous Hollywood films.
  • B. Agnes Ramsay
    Agnes Ramsay was a notable member of the Ramsay family, recognized for bearing the Ramsay surname in historical records.
  • C. Agnes Syme
    Agnes Syme was the wife of pioneering British surgeon and antiseptic surgery innovator Joseph Lister.
  • D. Mary Agnew
    Mary Agnew was the first wife of American poet and travel writer Bayard Taylor, remembered primarily through her brief, tragic marriage to him.
  • E. Agnes Smith
    Agnes Smith is the daughter of Mrs. Anna Smith.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007f4f9d48190b96a7e0c6993cd69 completed April 15, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd491cd881908bad9660af9b6b8f completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 3:13 a.m.