Triple

T14537000
Position Surface form Disambiguated ID Type / Status
Subject Hamish Linklater E341070 entity
Predicate mother P120 FINISHED
Object Kristin Linklater E380917 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: Kristin Linklater | Statement: [Hamish Linklater, mother, Kristin Linklater]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kristin Linklater
Context triple: [Hamish Linklater, mother, Kristin Linklater]
  • A. Kristin Linklater chosen
    Kristin Linklater was a renowned Scottish vocal coach, teacher, and author best known for her influential work on voice training for actors and her long association with Shakespearean performance.
  • B. Lorelei Linklater
    Lorelei Linklater is an American actress best known for her role as the protagonist’s sister in Richard Linklater’s coming-of-age film "Boyhood."
  • C. Elizabeth Burns
    Elizabeth Burns was a daughter of the Scottish poet Robert Burns, known primarily through her connection to his family and legacy.
  • D. Meg Tilly
    Meg Tilly is a Canadian-American actress and novelist best known for her Academy Award–nominated performance in the film "Agnes of God."
  • E. Maria Bello
    Maria Bello is an American actress known for her versatile roles in film and television, including performances in projects like "A History of Violence," "ER," and "NCIS."
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb1bb90008190947ac0961393446d completed April 14, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a5ae04881909e7eb766fca33066 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.