Triple

T23071354
Position Surface form Disambiguated ID Type / Status
Subject Blackstone Square E575202 entity
Predicate hasAdjacentPark P13799 FINISHED
Object Franklin Square 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: Franklin Square | Statement: [Blackstone Square, hasAdjacentPark, Franklin Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franklin Square
Context triple: [Blackstone Square, hasAdjacentPark, Franklin Square]
  • A. Franklin Square
    Franklin Square is one of Philadelphia’s original five public squares, now a historic urban park featuring fountains, family attractions, and green space in the Old City area.
  • B. Franklin Square
    Franklin Square is a historic public square in Savannah, Georgia, known for its 18th- and 19th-century architecture and role in the city’s distinctive grid of landscaped squares.
  • C. Franklin Square
    Franklin Square is a suburban hamlet in Nassau County, Long Island, known as a residential community just outside New York City.
  • D. Franklin Square
    Franklin Square is a historic public park and urban green space located in downtown Washington, D.C.
  • E. Franklin Square chosen
    Franklin Square is a historic public park located in Boston’s South End neighborhood, known for its tree-lined paths and Victorian-era surroundings.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c5ffad881909ed626045c15dd33 completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.