Triple

T11253601
Position Surface form Disambiguated ID Type / Status
Subject Jonathan Trelawny E266381 entity
Predicate mother P120 FINISHED
Object Mary Seymour E372424 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: Mary Seymour | Statement: [Jonathan Trelawny, mother, Mary Seymour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Seymour
Context triple: [Jonathan Trelawny, mother, Mary Seymour]
  • A. Mary Seymour chosen
    Mary Seymour was the short-lived daughter of Queen Catherine Parr and Thomas Seymour, born into the tumultuous politics of the Tudor court.
  • B. Mary Cecil
    Mary Cecil was a member of the prominent Cecil family of the English nobility, daughter of Thomas Cecil, 1st Earl of Exeter.
  • C. Elizabeth Seymour
    Elizabeth Seymour was an 18th-century British noblewoman who became Duchess of Northumberland through her marriage to Hugh Percy, 1st Duke of Northumberland.
  • D. Elizabeth Seymour
    Elizabeth Seymour was a 16th-century English noblewoman of the prominent Seymour family, connected to the Tudor court through her siblings and marriages.
  • E. Nerissa Bowes-Lyon
    Nerissa Bowes-Lyon was a first cousin of Queen Elizabeth II who spent most of her life in a long-stay hospital for people with learning disabilities, largely hidden from public view.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e933648481909873094bc89ed041 completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4cc941d34819099ae30713bdd03e5 completed April 19, 2026, 12:37 p.m.
Created at: April 8, 2026, 9:31 p.m.