Triple

T7799941
Position Surface form Disambiguated ID Type / Status
Subject Metuchen, New Jersey E180402 entity
Predicate hasElementarySchool P113 FINISHED
Object Moss School
Moss School is a public elementary school serving young students in the borough of Metuchen, New Jersey.
E695569 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: Moss School | Statement: [Metuchen, New Jersey, hasElementarySchool, Moss School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moss School
Context triple: [Metuchen, New Jersey, hasElementarySchool, Moss School]
  • A. South School
    South School is a public elementary school serving early-grade students in the New Canaan, Connecticut community.
  • B. South School
    South School is a public elementary school serving young students in the town of Stoneham, Massachusetts.
  • C. John Mason School
    John Mason School is a secondary school located in the town of Abingdon in Oxfordshire, England.
  • D. Morse School
    Morse School is a public elementary school in Cambridge, Massachusetts, serving students within the Cambridge Public Schools district.
  • E. Kateri School
    Kateri School is an educational institution serving the community of Kahnawà:ke, a Mohawk territory near Montreal, Canada.
  • 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: Moss School
Triple: [Metuchen, New Jersey, hasElementarySchool, Moss School]
Generated description
Moss School is a public elementary school serving young students in the borough of Metuchen, New Jersey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Moss School
Target entity description: Moss School is a public elementary school serving young students in the borough of Metuchen, New Jersey.
  • A. South School
    South School is a public elementary school serving early-grade students in the New Canaan, Connecticut community.
  • B. South School
    South School is a public elementary school serving young students in the town of Stoneham, Massachusetts.
  • C. John Mason School
    John Mason School is a secondary school located in the town of Abingdon in Oxfordshire, England.
  • D. Morse School
    Morse School is a public elementary school in Cambridge, Massachusetts, serving students within the Cambridge Public Schools district.
  • E. Kateri School
    Kateri School is an educational institution serving the community of Kahnawà:ke, a Mohawk territory near Montreal, Canada.
  • 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_69ca827e50cc8190a92a733577184938 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cae985d8f08190b38d9d6848a7dc83 completed March 30, 2026, 9:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb142117b48190bdc17677592bfa8f completed March 31, 2026, 12:24 a.m.
NEDg Description generation batch_69cb1a1414a08190912945cee30e6bc2 completed March 31, 2026, 12:49 a.m.
NED2 Entity disambiguation (via description) batch_69cb3843368881908d7c4d5a81c53a23 completed March 31, 2026, 2:58 a.m.
Created at: March 30, 2026, 4:33 p.m.