Triple

T40256
Position Surface form Disambiguated ID Type / Status
Subject Harrow School E795 entity
Predicate hasCampusFeature P2465 FINISHED
Object Old Schools
Old Schools is a historic building complex within Harrow School that houses some of the institution’s oldest classrooms and academic facilities.
 E795 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: Old Schools | Statement: [Harrow School, hasCampusFeature, Old Schools]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Old Schools
Context triple: [Harrow School, hasCampusFeature, Old Schools]
  • A. Butler School
    Butler School is a public elementary school serving young students in the town of Belmont, Massachusetts.
  • B. Old Campus
    Old Campus is Yale University's historic central quadrangle, known for its iconic collegiate Gothic architecture and first-year student residences.
  • C. Harrow School
    Harrow School is a prestigious independent boarding school for boys in London, England, renowned for educating numerous prominent figures in British political and cultural life.
  • D. Winn Brook School
    Winn Brook School is a public elementary school serving young students in the Belmont, Massachusetts community.
  • E. Luitpold Gymnasium
    Luitpold Gymnasium was a secondary school in Munich, Germany, known for being one of the early educational institutions attended by Albert Einstein.
  • 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: Old Schools
Triple: [Harrow School, hasCampusFeature, Old Schools]
Generated description
Old Schools is a historic building complex within Harrow School that houses some of the institution’s oldest classrooms and academic facilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Old Schools
Target entity description: Old Schools is a historic building complex within Harrow School that houses some of the institution’s oldest classrooms and academic facilities.
  • A. Butler School
    Butler School is a public elementary school serving young students in the town of Belmont, Massachusetts.
  • B. Old Campus
    Old Campus is Yale University's historic central quadrangle, known for its iconic collegiate Gothic architecture and first-year student residences.
  • C. Harrow School chosen
    Harrow School is a prestigious independent boarding school for boys in London, England, renowned for educating numerous prominent figures in British political and cultural life.
  • D. Winn Brook School
    Winn Brook School is a public elementary school serving young students in the Belmont, Massachusetts community.
  • E. Luitpold Gymnasium
    Luitpold Gymnasium was a secondary school in Munich, Germany, known for being one of the early educational institutions attended by Albert Einstein.
  • F. None of above.

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_69a247a8f6c08190bac804906d62ed5a completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a24ec1ef5481909daf99654dfa3f57 completed Feb. 28, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a255338b6c8190bb31101691ce689a completed Feb. 28, 2026, 2:38 a.m.
NEDg Description generation batch_69a255ee9c1c8190a9d1db89af34fbaf completed Feb. 28, 2026, 2:41 a.m.
NED2 Entity disambiguation (via description) batch_69a256a35c3081908aa5522c734bd54d completed Feb. 28, 2026, 2:44 a.m.
Created at: Feb. 28, 2026, 1:46 a.m.