Triple

T15864527
Position Surface form Disambiguated ID Type / Status
Subject Canton, South Dakota E384674 entity
Predicate hasHighSchool P113 FINISHED
Object Canton High School
Canton High School is a public secondary school serving students in the Canton, South Dakota community.
E1182525 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: Canton High School | Statement: [Canton, South Dakota, hasHighSchool, Canton High School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canton High School
Context triple: [Canton, South Dakota, hasHighSchool, Canton High School]
  • A. Washington High School
    Washington High School is a public secondary school in California that serves students in the Fremont Unified School District.
  • B. Clinton High School
    Clinton High School is a public secondary school serving students in the city of Clinton and surrounding areas in Anderson County, Tennessee.
  • C. Clinton High School
    Clinton High School is the public secondary school serving students in the town of Clinton, Massachusetts.
  • D. Sullivan High School
    Sullivan High School is a public secondary school serving students in the small city of Sullivan in southwestern Indiana.
  • E. Andrew High School
    Andrew High School is a public secondary school in Tinley Park, Illinois, known for serving students in the southwest suburbs of Chicago.
  • 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: Canton High School
Triple: [Canton, South Dakota, hasHighSchool, Canton High School]
Generated description
Canton High School is a public secondary school serving students in the Canton, South Dakota community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Canton High School
Target entity description: Canton High School is a public secondary school serving students in the Canton, South Dakota community.
  • A. Canton High School
    Canton High School is a public secondary school serving the community of Canton, Massachusetts.
  • B. Washington High School
    Washington High School is a public secondary school in California that serves students in the Fremont Unified School District.
  • C. Clinton High School
    Clinton High School is a public secondary school serving students in the city of Clinton and surrounding areas in Anderson County, Tennessee.
  • D. Clinton High School
    Clinton High School is the public secondary school serving students in the town of Clinton, Massachusetts.
  • E. Sullivan High School
    Sullivan High School is a public secondary school serving students in the small city of Sullivan in southwestern Indiana.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1555e4ee48190a3b27b4ab9bdb1c8 completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb03ef4e48190abe431e6abc9ef9c completed May 9, 2026, 10:07 p.m.
NEDg Description generation batch_69ffb10004448190aa176a04249b9429 completed May 9, 2026, 10:11 p.m.
NED2 Entity disambiguation (via description) batch_69ffb177d4808190989c3ce8397128b4 completed May 9, 2026, 10:13 p.m.
Created at: April 10, 2026, 4:50 a.m.