Triple

T19264632
Position Surface form Disambiguated ID Type / Status
Subject San Lorenzo E481737 entity
Predicate hasElementarySchool P113 FINISHED
Object Washington Manor Middle School
Washington Manor Middle School is a public middle school serving students in the San Lorenzo area of California.
E1367175 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: Washington Manor Middle School | Statement: [San Lorenzo, hasElementarySchool, Washington Manor Middle School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Washington Manor Middle School
Context triple: [San Lorenzo, hasElementarySchool, Washington Manor Middle School]
  • A. Wood Middle School
    Wood Middle School is a public middle school located in Alameda, California, serving students in grades 6–8 within the Alameda Unified School District.
  • B. South Middle School
    South Middle School is a public middle school in Braintree, Massachusetts, serving students in the Braintree Public Schools district.
  • C. Stone Middle School
    Stone Middle School is a public middle school serving students in the Centreville area.
  • D. Woodlawn Middle School
    Woodlawn Middle School is a public middle school serving students in the Woodlawn community of Maryland.
  • E. Oak Middle School
    Oak Middle School is a public middle school serving students in the town of Shrewsbury, Massachusetts.
  • 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: Washington Manor Middle School
Triple: [San Lorenzo, hasElementarySchool, Washington Manor Middle School]
Generated description
Washington Manor Middle School is a public middle school serving students in the San Lorenzo area of California.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Washington Manor Middle School
Target entity description: Washington Manor Middle School is a public middle school serving students in the San Lorenzo area of California.
  • A. Wood Middle School
    Wood Middle School is a public middle school located in Alameda, California, serving students in grades 6–8 within the Alameda Unified School District.
  • B. South Middle School
    South Middle School is a public middle school in Braintree, Massachusetts, serving students in the Braintree Public Schools district.
  • C. Stone Middle School
    Stone Middle School is a public middle school serving students in the Centreville area.
  • D. Woodlawn Middle School
    Woodlawn Middle School is a public middle school serving students in the Woodlawn community of Maryland.
  • E. Oak Middle School
    Oak Middle School is a public middle school serving students in the town of Shrewsbury, Massachusetts.
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8bce6881908395836960762672 completed April 20, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a070e6cfcc481909b324c2a1cc0af71 completed May 15, 2026, 12:15 p.m.
NEDg Description generation batch_6a070ee343008190a1be4338889ae540 completed May 15, 2026, 12:17 p.m.
NED2 Entity disambiguation (via description) batch_6a070f5c89348190925244dd0460bcdc completed May 15, 2026, 12:19 p.m.
Created at: April 10, 2026, 1:29 p.m.