Triple

T12945366
Position Surface form Disambiguated ID Type / Status
Subject Niagara Square E309747 entity
Predicate streetRadiatingFrom P72721 FINISHED
Object Porter Avenue 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: Porter Avenue | Statement: [Niagara Square, streetRadiatingFrom, Porter Avenue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porter Avenue
Context triple: [Niagara Square, streetRadiatingFrom, Porter Avenue]
  • A. Porter Avenue chosen
    Porter Avenue is a historic, Olmsted-designed boulevard in Buffalo, New York, that forms part of the city’s landmark park and parkway system.
  • B. Landis Avenue
    Landis Avenue is the primary commercial thoroughfare and downtown business corridor in Vineland, New Jersey.
  • C. Willis Avenue
    Willis Avenue is a significant thoroughfare in the South Bronx, New York City, known for connecting major commercial and transit hubs in the area.
  • D. Warren Avenue
    Warren Avenue is a historic roadway on the Gettysburg Battlefield in Pennsylvania, running near Big Round Top and associated with key movements during the Civil War battle.
  • E. Warren Avenue
    Warren Avenue is a major east–west thoroughfare in the Detroit metropolitan area that serves as a key commercial and commuter route through Dearborn Heights, Michigan.
  • 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9804b743c8190810dc5c14bc6d912 completed April 10, 2026, 10:57 p.m.
Created at: April 9, 2026, 5:43 p.m.