Triple

T8030662
Position Surface form Disambiguated ID Type / Status
Subject Hannah Fry E186969 entity
Predicate name P16 FINISHED
Object Hannah Fry E186969 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: Hannah Fry | Statement: [Hannah Fry, name, Hannah Fry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hannah Fry
Context triple: [Hannah Fry, name, Hannah Fry]
  • A. Hannah Fry chosen
    Hannah Fry is a British mathematician, author, and broadcaster known for popularizing mathematics and data science through books, documentaries, and public lectures.
  • B. Carol Vorderman
    Carol Vorderman is a British media personality and television presenter best known for co-hosting the game show "Countdown" for over two decades.
  • C. Edwina Jean Vorderman
    Edwina Jean Vorderman is the mother of British television presenter and former Countdown co-host Carol Vorderman.
  • D. Maggie Antrobus
    Maggie Antrobus is a central figure in Thornton Wilder’s play "The Skin of Our Teeth," representing the resilient, everywoman matriarch who endures and adapts through a series of apocalyptic crises.
  • E. Denise Miller
    Denise Miller is an American actress best known for her television work in the late 1970s and early 1980s, including prominent roles in sitcoms.
  • 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_69ca82ad4e2c8190a693e3c9e30fe66f completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3eef921081908d0ea21f142c175a completed March 31, 2026, 3:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56e812dc81908916fc7163ae344a completed March 31, 2026, 11:21 p.m.
Created at: March 30, 2026, 5:22 p.m.