Triple

T17562439
Position Surface form Disambiguated ID Type / Status
Subject South Baltimore E427724 entity
Predicate contains P35 FINISHED
Object Locust Point 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: Locust Point | Statement: [South Baltimore, contains, Locust Point]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Locust Point
Context triple: [South Baltimore, contains, Locust Point]
  • A. Locust Point chosen
    Locust Point is a historic waterfront neighborhood in Baltimore known for its industrial roots, immigrant history, and views of the Inner Harbor.
  • B. Locust Point
    Locust Point is a residential waterfront neighborhood in the southeastern Bronx, New York City, known for its views of Eastchester Bay and suburban-like character.
  • C. Burleith
    Burleith is a residential neighborhood in northwest Washington, D.C., known for its tree-lined streets and proximity to Georgetown and the Georgetown University campus.
  • D. River Hill
    River Hill is a residential village and community within the planned city of Columbia, Maryland.
  • E. Belden Point
    Belden Point is a historic waterfront area at the southern tip of City Island in the Bronx, known for its views of the Long Island Sound and maritime character.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e456274c888190ac80402e391674dd completed April 19, 2026, 4:12 a.m.
Created at: April 10, 2026, 5:50 a.m.