Triple

T21463330
Position Surface form Disambiguated ID Type / Status
Subject Ken Russell E529528 entity
Predicate directed P7373 FINISHED
Object Tommy 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: Tommy | Statement: [Ken Russell, directed, Tommy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tommy
Context triple: [Ken Russell, directed, Tommy]
  • A. Tommy
    Tommy is a masculine given name, often a diminutive of Thomas, used in various English-speaking countries.
  • B. Tommy chosen
    Tommy is a landmark 1969 rock opera album by the British band The Who, telling the story of a "deaf, dumb, and blind" boy and widely regarded as one of the most influential concept albums in rock history.
  • C. Tommy
    "Tommy" is a famous poem by Rudyard Kipling that explores the contrasting ways British society treats soldiers in peacetime versus wartime.
  • D. Tommy
    Tommy is a colloquial nickname for Thomson's gazelle, a small, fast antelope native to the grasslands of East Africa.
  • E. Tommy
    Tommy is one of the alternate personalities (alters) of the soap opera character Victoria "Viki" Lord from the series One Life to Live.
  • 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_69e0c458133481908ae8b41a12c4edec completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9e9efdb188190be79b72e1bd18860 completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:09 p.m.