Triple

T11495137
Position Surface form Disambiguated ID Type / Status
Subject Marian Brook E272513 entity
Predicate relative P37 FINISHED
Object Ada Brook E929098 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: Ada Brook | Statement: [Marian Brook, relative, Ada Brook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ada Brook
Context triple: [Marian Brook, relative, Ada Brook]
  • A. Ada Brook chosen
    Ada Brook is a central character in the period drama series "The Gilded Age," portrayed as a genteel, unmarried woman navigating New York high society alongside her more domineering sister.
  • B. Ada Law
    Ada Law is one of the children of English actor Jude Law.
  • C. Anita Borg
    Anita Borg was an influential computer scientist and advocate for women in technology, best known for founding the Institute for Women and Technology (now AnitaB.org) and co-founding the Grace Hopper Celebration of Women in Computing.
  • D. Esther Dyson
    Esther Dyson is a prominent technology investor, journalist, and philanthropist known for her early involvement in the digital economy and advocacy on issues such as health, space, and technology policy.
  • E. Kathryn Bostic
    Kathryn Bostic is an American composer and pianist known for her evocative film and theater scores, particularly in independent cinema and stage productions.
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85de183f08190abfa36eaabc61dc6 completed April 10, 2026, 2:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69e624c3691081908f2e448aebab40aa completed April 20, 2026, 1:06 p.m.
Created at: April 8, 2026, 9:36 p.m.