Triple

T17856797
Position Surface form Disambiguated ID Type / Status
Subject Michael Howard E445958 entity
Predicate spouse P13 FINISHED
Object Sandra Howard 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: Sandra Howard | Statement: [Michael Howard, spouse, Sandra Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandra Howard
Context triple: [Michael Howard, spouse, Sandra Howard]
  • A. Sandra Howard chosen
    Sandra Howard is a British former fashion model and novelist who became known as the wife of Conservative politician Michael Howard.
  • B. Sandra Jennings
    Sandra Jennings is an American woman best known for her long-term relationship and legal disputes with actor William Hurt.
  • C. Sandra Jolley
    Sandra Jolley was the wife of American businessman and quality management expert Philip Crosby.
  • D. Sandra Nelson
    Sandra Nelson is an American actress known for her roles in film and television, including a part in the Cole Porter biographical musical film "De-Lovely."
  • E. Sandra Newman
    Sandra Newman is an American novelist and writer known for her inventive, genre-blending fiction and works such as "The Country of Ice Cream Star" and "The Men."
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4978bd5e081909e192f6aada5235f completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.