Triple

T5242307
Position Surface form Disambiguated ID Type / Status
Subject Andrew Getty E118371 entity
Predicate educatedAt P5 FINISHED
Object Town School for Boys
Town School for Boys is a private all-boys elementary and middle school in San Francisco known for serving the city’s affluent families.
E510636 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: Town School for Boys | Statement: [Andrew Getty, educatedAt, Town School for Boys]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Town School for Boys
Context triple: [Andrew Getty, educatedAt, Town School for Boys]
  • A. West School
    West School is a public elementary school serving students in the New Canaan, Connecticut community.
  • B. Bishop Wordsworth’s School
    Bishop Wordsworth’s School is a historic Church of England grammar school for boys located in the cathedral city of Salisbury, Wiltshire, England.
  • C. South School
    South School is a public elementary school serving early-grade students in the New Canaan, Connecticut community.
  • D. South School
    South School is a public elementary school serving young students in the town of Stoneham, Massachusetts.
  • E. Middlesex School
    Middlesex School is a prestigious private coeducational boarding and day preparatory school in Concord, Massachusetts, known for its rigorous academics and notable alumni.
  • 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: Town School for Boys
Triple: [Andrew Getty, educatedAt, Town School for Boys]
Generated description
Town School for Boys is a private all-boys elementary and middle school in San Francisco known for serving the city’s affluent families.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Town School for Boys
Target entity description: Town School for Boys is a private all-boys elementary and middle school in San Francisco known for serving the city’s affluent families.
  • A. West School
    West School is a public elementary school serving students in the New Canaan, Connecticut community.
  • B. Bishop Wordsworth’s School
    Bishop Wordsworth’s School is a historic Church of England grammar school for boys located in the cathedral city of Salisbury, Wiltshire, England.
  • C. South School
    South School is a public elementary school serving early-grade students in the New Canaan, Connecticut community.
  • D. South School
    South School is a public elementary school serving young students in the town of Stoneham, Massachusetts.
  • E. Middlesex School
    Middlesex School is a prestigious private coeducational boarding and day preparatory school in Concord, Massachusetts, known for its rigorous academics and notable alumni.
  • 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_69bd4467db0881909b3b0982df32cc8f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b4c6fa8819099442b1b110e51fb completed March 20, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10ca0a1c8190a3cc0537886281e5 completed March 21, 2026, 9:42 p.m.
NEDg Description generation batch_69bf1280a8e08190a99d20e50b468afb completed March 21, 2026, 9:49 p.m.
NED2 Entity disambiguation (via description) batch_69bf12e32f248190977820dd1220db22 completed March 21, 2026, 9:51 p.m.
Created at: March 20, 2026, 1:49 p.m.