Triple

T3617109
Position Surface form Disambiguated ID Type / Status
Subject Race Street E76628 entity
Predicate near P350 FINISHED
Object Franklin Square E136299 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: Franklin Square | Statement: [Race Street, near, Franklin Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franklin Square
Context triple: [Race Street, near, Franklin Square]
  • A. Franklin Square chosen
    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 suburban hamlet in Nassau County, Long Island, known as a residential community just outside New York City.
  • C. Franklin Square
    Franklin Square is a historic public park and urban green space located in downtown Washington, D.C.
  • D. Sullivan Square
    Sullivan Square is a neighborhood in the Charlestown area of Boston, Massachusetts, known historically as a major transportation hub and gateway to the city.
  • E. Herald Square
    Herald Square is a bustling commercial and transportation hub in Midtown Manhattan, best known for its flagship Macy’s department store and as a focal point of New York City’s retail and holiday festivities.
  • 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_69ad85dae2fc81908d1ceadbc6af0089 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc27dd030819083d34fee0c06612a completed March 8, 2026, 6:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4331a82688190add137b1f68c955e completed March 13, 2026, 3:54 p.m.
Created at: March 8, 2026, 3:23 p.m.