Triple

T15504677
Position Surface form Disambiguated ID Type / Status
Subject Uptown Saint John E379049 entity
Predicate hasPart P35 FINISHED
Object Queen Square
Queen Square is a historic public park and green space located in the Uptown area of Saint John, New Brunswick.
 E1162892 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: Queen Square | Statement: [Uptown Saint John, hasPart, Queen Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Queen Square
Context triple: [Uptown Saint John, hasPart, Queen Square]
  • A. Queen Square
    Queen Square is a historic public square located in the coastal city of Brunswick, Georgia.
  • B. Queen Square
    Queen Square is a historic garden square in the Bloomsbury district of central London, known for its Georgian architecture and nearby medical and academic institutions.
  • C. Queen’s Square
    Queen’s Square is a prominent public space and cultural focal point in downtown Galt, Cambridge, Ontario, known for hosting community events and gatherings.
  • D. Queen’s Square
    Queen’s Square is a residential neighborhood within Belize City, Belize.
  • E. Queen Square, Bristol
    Queen Square, Bristol is a historic Georgian garden square in central Bristol, England, known for its elegant 18th-century architecture and landscaped public green space.
  • 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: Queen Square
Triple: [Uptown Saint John, hasPart, Queen Square]
Generated description
Queen Square is a historic public park and green space located in the Uptown area of Saint John, New Brunswick.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Queen Square
Target entity description: Queen Square is a historic public park and green space located in the Uptown area of Saint John, New Brunswick.
  • A. Queen Square
    Queen Square is a historic public square located in the coastal city of Brunswick, Georgia.
  • B. Queen Square
    Queen Square is a historic garden square in the Bloomsbury district of central London, known for its Georgian architecture and nearby medical and academic institutions.
  • C. Queen’s Square
    Queen’s Square is a prominent public space and cultural focal point in downtown Galt, Cambridge, Ontario, known for hosting community events and gatherings.
  • D. Queen’s Square
    Queen’s Square is a residential neighborhood within Belize City, Belize.
  • E. Queen Square, Bristol
    Queen Square, Bristol is a historic Georgian garden square in central Bristol, England, known for its elegant 18th-century architecture and landscaped public green space.
  • 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_69d85cd53a7c819080f5b9042c4c199e completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03fcd5d948190b25a67a72ef980e9 completed April 16, 2026, 1:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff454ca0f0819088ba846a448dda2e completed May 9, 2026, 2:31 p.m.
NEDg Description generation batch_69ff466b2f58819098c98b44548f4ce9 completed May 9, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69ff46a192288190b7fd6db18bfc1fca completed May 9, 2026, 2:37 p.m.
Created at: April 10, 2026, 3:54 a.m.