Triple

T552450
Position Surface form Disambiguated ID Type / Status
Subject Tom Hooper E11868 entity
Predicate directed P7373 FINISHED
Object Longford E69127 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: Longford | Statement: [Tom Hooper, directed, Longford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Longford
Context triple: [Tom Hooper, directed, Longford]
  • A. Longford chosen
    Longford is a 2006 British television drama film directed by Tom Hooper that portrays the controversial relationship between Lord Longford and Moors murderer Myra Hindley.
  • B. Cashel
    Cashel is a former parliamentary constituency in Ireland that was once represented in the British Parliament by statesman Sir Robert Peel.
  • C. County Antrim
    County Antrim is a historic county in the northeast of Northern Ireland, known for its rugged coastline, the Giant’s Causeway, and the city of Belfast.
  • D. Dublin Region
    Dublin Region is an administrative and statistical area in eastern Ireland that encompasses the city of Dublin and its surrounding suburban counties.
  • E. Leinster
    Leinster is a province in eastern Ireland that includes the capital city, Dublin, and is the country’s most populous region.
  • 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_69a4932941d08190815efd422f0b4ca7 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a499047bd4819089ca8345f1b6e46c completed March 1, 2026, 7:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4e632e7c48190b211f7fcc4903dea completed March 2, 2026, 1:21 a.m.
Created at: March 1, 2026, 7:32 p.m.