Triple

T11518709
Position Surface form Disambiguated ID Type / Status
Subject Regent Park E273099 entity
Predicate borderedBy P224 FINISHED
Object River Street
River Street is a roadway in Toronto, Ontario, running along the eastern edge of the Regent Park neighborhood.
 E929900 NE FINISHED

How this triple was built (4 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: River Street | Statement: [Regent Park, borderedBy, River Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: River Street
Context triple: [Regent Park, borderedBy, River Street]
  • A. River Street
    River Street is a roadway in Cambridge’s city center that serves as a key connector through the urban core.
  • B. River Street
    River Street is a notable thoroughfare and local landmark in the Mattapan neighborhood of Boston, Massachusetts.
  • C. River Street
    River Street is a historic waterfront thoroughfare in Savannah, Georgia, known for its cobblestone streets, shops, restaurants, and views along the Savannah River.
  • D. Colon Street
    Colon Street is a historic and bustling commercial thoroughfare in Cebu City, Philippines, known as the oldest street in the country.
  • E. North Orleans Street
    North Orleans Street is a major north–south thoroughfare in Chicago that runs through downtown and the Near North Side, connecting commercial, residential, and historic districts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: River Street
Triple: [Regent Park, borderedBy, River Street]
Generated description
River Street is a roadway in Toronto, Ontario, running along the eastern edge of the Regent Park neighborhood.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: River Street
Target entity description: River Street is a roadway in Toronto, Ontario, running along the eastern edge of the Regent Park neighborhood.
  • A. River Street
    River Street is a roadway in Cambridge’s city center that serves as a key connector through the urban core.
  • B. River Street
    River Street is a notable thoroughfare and local landmark in the Mattapan neighborhood of Boston, Massachusetts.
  • C. River Street
    River Street is a historic waterfront thoroughfare in Savannah, Georgia, known for its cobblestone streets, shops, restaurants, and views along the Savannah River.
  • D. Colon Street
    Colon Street is a historic and bustling commercial thoroughfare in Cebu City, Philippines, known as the oldest street in the country.
  • E. North Orleans Street
    North Orleans Street is a major north–south thoroughfare in Chicago that runs through downtown and the Near North Side, connecting commercial, residential, and historic districts.
  • F. None of above. chosen

Provenance (5 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fcf927081908ef89eff7ad833b0 completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e62530a6b08190a8ba3c410e79cf72 completed April 20, 2026, 1:08 p.m.
NEDg Description generation batch_69e62cf5b9988190bc1935993f0111f7 completed April 20, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_69e66433ddb48190994bb1160b0ff732 completed April 20, 2026, 5:36 p.m.
Created at: April 8, 2026, 9:36 p.m.