Triple

T22573963
Position Surface form Disambiguated ID Type / Status
Subject Digging for Fire E544344 entity
Predicate starring P1507 FINISHED
Object Judith Light NE NERFINISHED

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: Judith Light | Statement: [Digging for Fire, starring, Judith Light]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Judith Light
Context triple: [Digging for Fire, starring, Judith Light]
  • A. Judith Light chosen
    Judith Light is an American actress known for her acclaimed work in television, film, and theater, including roles in series like "Who's the Boss?" and "Transparent."
  • B. Beth Leavel
    Beth Leavel is a Tony Award–winning American stage actress and singer best known for her work in numerous Broadway musicals.
  • C. Linda Purl
    Linda Purl is an American actress and singer best known for her roles on television series such as "Happy Days," "Matlock," and "The Office."
  • D. Rachel Messerer
    Rachel Messerer was a member of the prominent Messerer family of Russian ballet, known as a relative of legendary ballerina Maya Plisetskaya.
  • E. Anne McDonnell
    Anne McDonnell was an American socialite best known as the first wife of industrialist Henry Ford II.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e30d05481909df915354c89f0d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f15fea683c81908fbf9f171eed3341 completed April 29, 2026, 1:33 a.m.
Created at: April 16, 2026, 8:53 p.m.