Triple

T5514936
Position Surface form Disambiguated ID Type / Status
Subject Dangerous E144657 entity
Predicate hasCastMember P2308 FINISHED
Object Alison Skipworth E542257 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: Alison Skipworth | Statement: [Dangerous, hasCastMember, Alison Skipworth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alison Skipworth
Context triple: [Dangerous, hasCastMember, Alison Skipworth]
  • A. Alison Skipworth chosen
    Alison Skipworth was a British-born character actress of the early 20th century, known for her sharp-tongued, often aristocratic roles in American stage and film comedies.
  • B. Gillian Siddall
    Gillian Siddall is a Canadian academic and university administrator who serves as president of Lakehead University.
  • C. Alison Moore
    Alison Moore is an Australian lexicographer who serves as the editor-in-chief of the Macquarie Dictionary, a leading dictionary of Australian English.
  • D. Alison Bashford
    Alison Bashford is a prominent Australian historian known for her influential work on global history, environmental history, and the history of science, medicine, and population.
  • E. Alison Brown
    Alison Brown is a film industry professional best known for her role in founding the American animation company Blue Sky Studios.
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f5b4e988190b590b4157cf089c1 completed March 22, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07d567cb48190839f340041f2300b completed March 22, 2026, 11:37 p.m.
Created at: March 22, 2026, 3:33 p.m.