Triple

T6208411
Position Surface form Disambiguated ID Type / Status
Subject Tor Johnson E138805 entity
Predicate workedWith P398 FINISHED
Object Ed Wood E62945 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: Ed Wood | Statement: [Tor Johnson, workedWith, Ed Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Wood
Context triple: [Tor Johnson, workedWith, Ed Wood]
  • A. Ed Wood chosen
    Ed Wood is a 1994 biographical comedy-drama film directed by Tim Burton that portrays the life and eccentric filmmaking career of cult director Edward D. Wood Jr.
  • B. Edward Wood
    Edward Wood, later known as Lord Irwin and Earl of Halifax, was a prominent British Conservative politician and diplomat who served as Viceroy of India and Foreign Secretary in the early 20th century.
  • C. John Waters
    John Waters is an Australian actor known for his work in film, television, and theatre, including prominent roles in historical dramas and popular TV series.
  • D. Waiting for Guffman
    Waiting for Guffman is a 1996 mockumentary comedy film directed by Christopher Guest that satirizes small-town community theater through an eccentric cast of aspiring performers.
  • E. David Griswold
    David Griswold is a software engineer best known for creating the Strongtalk implementation of the Smalltalk programming language, notable for its optional static type system and high performance.
  • 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_69c008ada364819096c9e92c74d639b5 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062870d5881909b8d4e33ff31a907 completed March 22, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16f52829c81909bdd422cbb1eabf4 completed March 23, 2026, 4:50 p.m.
Created at: March 22, 2026, 4:21 p.m.