Triple

T18823970
Position Surface form Disambiguated ID Type / Status
Subject Line of Fire E460335 entity
Predicate setting P1957 FINISHED
Object Richmond, Virginia 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: Richmond, Virginia | Statement: [Line of Fire, setting, Richmond, Virginia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richmond, Virginia
Context triple: [Line of Fire, setting, Richmond, Virginia]
  • A. Richmond, Virginia chosen
    Richmond, Virginia is the capital city of the U.S. state of Virginia, known for its pivotal role in American history, particularly as the capital of the Confederacy during the Civil War.
  • B. Richmond
    Richmond is an industrial and residential city in California’s East Bay region, known for its waterfront along San Francisco Bay and its diverse, working-class communities.
  • C. Richmond
    Richmond is an Australian federal electoral division in northern New South Wales that includes coastal communities such as Tweed Heads and Byron Bay.
  • D. Richmond
    Richmond is a historic outer suburb of Sydney, New South Wales, known for its semi-rural character and proximity to the Hawkesbury River.
  • E. Richmond
    Richmond is a small settlement located in St. Mary Parish on the northern coast of Jamaica.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6bce5588190bd0aefcd0c51edad completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:56 a.m.