Triple

T17054291
Position Surface form Disambiguated ID Type / Status
Subject Alumni Hall E413778 entity
Predicate city P40 FINISHED
Object Annapolis E22341 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: Annapolis | Statement: [Alumni Hall, city, Annapolis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Annapolis
Context triple: [Alumni Hall, city, Annapolis]
  • A. Annapolis chosen
    Annapolis is a historic U.S. city on the Chesapeake Bay known for its colonial architecture, maritime heritage, and as the home of the United States Naval Academy.
  • B. Salisbury, Maryland
    Salisbury, Maryland is a small city on Maryland’s Eastern Shore known as a regional commercial hub and the home of Salisbury University.
  • C. Georgetown, Maryland
    Georgetown, Maryland is a small census-designated community located in Kent County on Maryland’s Eastern Shore.
  • D. Aberdeen, Maryland
    Aberdeen, Maryland is a small city in Harford County best known as the home of the U.S. Army’s Aberdeen Proving Ground and for its proximity to the Chesapeake Bay.
  • E. Jefferson, Maryland
    Jefferson, Maryland is a small unincorporated community and historic rural town in Frederick County, known for its scenic setting in western Maryland and its 18th- and 19th-century architecture.
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3daa54c808190a6e8333c413f4e26 completed April 18, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ed60d3481909c8144bcb01316a1 completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:34 a.m.