Triple

T14579028
Position Surface form Disambiguated ID Type / Status
Subject Eliza Roberts E342134 entity
Predicate familyName P18 FINISHED
Object Roberts
Roberts is a common English-language surname borne by numerous notable individuals across fields such as politics, entertainment, sports, and academia.
E938305 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: Roberts | Statement: [Eliza Roberts, familyName, Roberts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roberts
Context triple: [Eliza Roberts, familyName, Roberts]
  • A. John
    John is the first name of Pete Ricketts, an American businessman and politician who has served as governor of Nebraska.
  • B. John
    John B. Magruder was a Confederate major general during the American Civil War, known for his leadership in the Peninsula Campaign and his flamboyant personality.
  • C. John
    John is the given name of John Baptist Purcell, a 19th-century Irish-American Roman Catholic archbishop of Cincinnati.
  • D. John
    John is the given name of John Foxe the Younger, an English clergyman and son of the martyrologist John Foxe.
  • E. John
    John is the first name of Captain Price, a prominent fictional British special forces soldier from the Call of Duty video game series.
  • 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: Roberts
Triple: [Eliza Roberts, familyName, Roberts]
Generated description
Roberts is a common English-language surname borne by numerous notable individuals across fields such as politics, entertainment, sports, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roberts
Target entity description: Roberts is a common English-language surname borne by numerous notable individuals across fields such as politics, entertainment, sports, and academia.
  • A. Roberts
    Roberts is the maiden surname of Margaret Thatcher, the former Prime Minister of the United Kingdom.
  • B. Roberts
    Roberts is the territorial designation associated with British Army commander Earl Roberts, a prominent military figure of the late 19th and early 20th centuries.
  • C. Roberts chosen
    Roberts is a common English and Welsh surname derived from the given name Robert, borne by numerous notable individuals across various fields.
  • D. John
    John is the first name of Pete Ricketts, an American businessman and politician who has served as governor of Nebraska.
  • E. John
    John Seigenthaler was an American journalist, editor, and civil rights advocate best known for his long tenure at The Tennessean and his work promoting First Amendment rights.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f6f78c81908a30ecb4c025299d completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ad03e7881908a783182c6d656b5 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c278e8481909465972b32ad6c28 completed May 8, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_69fd8ca921108190943eb948f9af6123 completed May 8, 2026, 7:11 a.m.
Created at: April 10, 2026, 1:24 a.m.