Triple

T8845700
Position Surface form Disambiguated ID Type / Status
Subject Ria Torres E210498 entity
Predicate worksWith P398 FINISHED
Object Gillian Foster E768866 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: Gillian Foster | Statement: [Ria Torres, worksWith, Gillian Foster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gillian Foster
Context triple: [Ria Torres, worksWith, Gillian Foster]
  • A. Gillian Foster chosen
    Gillian Foster is a central character in the TV series "Lie to Me," a psychologist and partner in the deception-detection firm Lightman Group.
  • B. Gillian Hanna
    Gillian Hanna was a British actress known for her work in film, television, and theatre, particularly in character roles.
  • C. Gail Buckley
    Gail Buckley is an American author and historian known for her works on African American history and her family’s legacy, including being the daughter of singer and civil rights activist Lena Horne.
  • D. Julie Ferguson
    Julie Ferguson is the wife of the late American actor and comedian Charles Grodin.
  • E. Lesley Laird
    Lesley Laird is a Scottish Labour politician who served as a Member of Parliament and has been involved in UK and Scottish politics, including holding frontbench roles in the Labour Party.
  • 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_69ca838967bc8190b46c3c80a2887ea4 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60a6623c8190ba43545544f58633 completed April 1, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05be377988190a59f0033322d627f completed April 4, 2026, 12:31 a.m.
Created at: March 30, 2026, 6:48 p.m.