Triple

T690117
Position Surface form Disambiguated ID Type / Status
Subject Robert Ross E13372 entity
Predicate spouse P13 FINISHED
Object Elizabeth Ross
Elizabeth Ross was the wife of Robert Ross, a British officer best known for his role in the War of 1812.
 E213747 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: Elizabeth Ross | Statement: [Robert Ross, spouse, Elizabeth Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Ross
Context triple: [Robert Ross, spouse, Elizabeth Ross]
  • A. Elizabeth Hartwell
    Elizabeth Hartwell was the wife of American Founding Father and statesman Roger Sherman.
  • B. Mary Carr
    Mary Carr was an American character actress of the silent and early sound film era, often cast as kindly maternal figures.
  • C. Mary Ingersoll
    Mary Ingersoll was the wife of American mathematician and navigator Nathaniel Bowditch, known primarily through her association with his life and work in early 19th-century New England.
  • D. Lydia Moore Parker
    Lydia Moore Parker was the wife of John Parker, a prominent early American frontiersman and Texas settler.
  • E. Elizabeth Hubbard
    Elizabeth Hubbard was a business associate of Florence Nightingale Graham, better known as Elizabeth Arden, involved in the early development of the cosmetics industry.
  • 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: Elizabeth Ross
Triple: [Robert Ross, spouse, Elizabeth Ross]
Generated description
Elizabeth Ross was the wife of Robert Ross, a British officer best known for his role in the War of 1812.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Ross
Target entity description: Elizabeth Ross was the wife of Robert Ross, a British officer best known for his role in the War of 1812.
  • A. Elizabeth Hartwell
    Elizabeth Hartwell was the wife of American Founding Father and statesman Roger Sherman.
  • B. Mary Carr
    Mary Carr was an American character actress of the silent and early sound film era, often cast as kindly maternal figures.
  • C. Mary Ingersoll
    Mary Ingersoll was the wife of American mathematician and navigator Nathaniel Bowditch, known primarily through her association with his life and work in early 19th-century New England.
  • D. Lydia Moore Parker
    Lydia Moore Parker was the wife of John Parker, a prominent early American frontiersman and Texas settler.
  • E. Elizabeth Hubbard
    Elizabeth Hubbard was a business associate of Florence Nightingale Graham, better known as Elizabeth Arden, involved in the early development of the cosmetics industry.
  • 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a0ad379c81909003d35c63822780 completed March 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69adeaad456481908cf9fb412bdf90f0 completed March 8, 2026, 9:31 p.m.
NEDg Description generation batch_69adee77b884819083b4c016f357cf62 completed March 8, 2026, 9:47 p.m.
NED2 Entity disambiguation (via description) batch_69adeee7a52881909b6994e1c9558fda completed March 8, 2026, 9:49 p.m.
Created at: March 1, 2026, 7:36 p.m.