Triple

T23419002
Position Surface form Disambiguated ID Type / Status
Subject William Lawrence James E560591 entity
Predicate familyName P18 FINISHED
Object James
James is a common English surname borne by numerous notable figures across history, including philosophers, writers, and political leaders.
E577893 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: James | Statement: [William Lawrence James, familyName, James]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James
Context triple: [William Lawrence James, familyName, James]
  • A. John
    John "Jack" Twyman was an American Hall of Fame professional basketball player best known for his scoring prowess with the Cincinnati Royals and his advocacy for teammate Maurice Stokes.
  • B. John
    John is the given name of American actor and voice artist John Ratzenberger, best known for playing Cliff Clavin on Cheers and voicing characters in Pixar films.
  • C. John
    John is the given first name of the legendary American professional golfer Byron Nelson, one of the sport’s early great champions.
  • D. John
    John is the middle name of William John Bertanzetti.
  • E. John
    John is the given name of John Stith Pemberton, the American pharmacist best known for inventing Coca-Cola.
  • 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: James
Triple: [William Lawrence James, familyName, James]
Generated description
James is a common English surname borne by numerous notable figures across history, including philosophers, writers, and political leaders.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: James
Target entity description: James is a common English surname borne by numerous notable figures across history, including philosophers, writers, and political leaders.
  • A. James chosen
    James is a common English surname of Hebrew origin, widely borne by notable figures in sports, politics, and the arts.
  • B. James
    James is a common masculine given name of Hebrew origin meaning "supplanter," widely used in English-speaking countries.
  • C. James
    James is the given name of James Hamilton, 3rd Duke of Abercorn, a British peer and politician.
  • D. James
    James is the middle name of Henry James Pye, an English poet who served as Poet Laureate of the United Kingdom in the late 18th and early 19th centuries.
  • E. James
    James is the middle name of Edward James Lennox, a prominent Canadian architect known for designing several landmark buildings in Toronto.
  • 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_69e2454cb1108190ab21ada5411a7146 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a54489d48190b2b2c29701851765 completed April 29, 2026, 6:29 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c67a145e88190a59c10b20d3395f9 completed May 19, 2026, 1:37 p.m.
NEDg Description generation batch_6a0c72156130819082e1d07262e144ca completed May 19, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0c76e904b08190a5329a3ed56291dc completed May 19, 2026, 2:42 p.m.
Created at: April 17, 2026, 5:43 p.m.