Triple

T1091033
Position Surface form Disambiguated ID Type / Status
Subject George Ellery Hale E24162 entity
Predicate middleName P143 FINISHED
Object Ellery
Ellery is the middle name of American solar astronomer George Ellery Hale, a pioneering figure in the development of modern astrophysics and major observatories.
E126142 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: Ellery | Statement: [George Ellery Hale, middleName, Ellery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellery
Context triple: [George Ellery Hale, middleName, Ellery]
  • A. Elliott
    Elliott is a masculine given name of English origin, often used as both a first name and a surname.
  • B. Evie
    Evie is a small coastal village and parish on the northwest of Mainland, Orkney, known for its rural landscape and nearby archaeological sites.
  • C. Lady Ella
    Lady Ella is the affectionate nickname of Ella Fitzgerald, the legendary American jazz singer renowned for her pure tone, impeccable diction, and virtuosic scat singing.
  • D. Chloe
    Chloe is the birth name of Nobel Prize–winning American novelist Toni Morrison, renowned for her powerful explorations of African American life and history.
  • E. Ellies
    The Ellies are annual awards recognizing excellence in magazine journalism and publishing, presented by the American Society of Magazine Editors.
  • 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: Ellery
Triple: [George Ellery Hale, middleName, Ellery]
Generated description
Ellery is the middle name of American solar astronomer George Ellery Hale, a pioneering figure in the development of modern astrophysics and major observatories.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ellery
Target entity description: Ellery is the middle name of American solar astronomer George Ellery Hale, a pioneering figure in the development of modern astrophysics and major observatories.
  • A. Elliott
    Elliott is a masculine given name of English origin, often used as both a first name and a surname.
  • B. Evie
    Evie is a small coastal village and parish on the northwest of Mainland, Orkney, known for its rural landscape and nearby archaeological sites.
  • C. Lady Ella
    Lady Ella is the affectionate nickname of Ella Fitzgerald, the legendary American jazz singer renowned for her pure tone, impeccable diction, and virtuosic scat singing.
  • D. Chloe
    Chloe is the birth name of Nobel Prize–winning American novelist Toni Morrison, renowned for her powerful explorations of African American life and history.
  • E. Ellies
    The Ellies are annual awards recognizing excellence in magazine journalism and publishing, presented by the American Society of Magazine Editors.
  • 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_69a49404428c819092dcc9632f5f7b8b completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b980c8448190b08c3a9a7e7f4e85 completed March 1, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac4c2a20b48190b3a550f6e5ee13e1 completed March 7, 2026, 4:02 p.m.
NEDg Description generation batch_69ac4cae760881909329701561ad2ba6 completed March 7, 2026, 4:05 p.m.
NED2 Entity disambiguation (via description) batch_69ac4d7176808190b74d535d7e1b7c6a completed March 7, 2026, 4:08 p.m.
Created at: March 1, 2026, 7:42 p.m.