Triple

T15638419
Position Surface form Disambiguated ID Type / Status
Subject John Marshall E376003 entity
Predicate givenName P17 FINISHED
Object John
John is the given name of John Marshall, the influential fourth Chief Justice of the United States who helped define the role of the Supreme Court and the development of American constitutional law.
E1168446 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: John | Statement: [John Marshall, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Marshall, givenName, John]
  • A. John
    John is the given name of John W. Mauchly, the American physicist and co-inventor of the ENIAC computer.
  • B. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • C. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • D. John
    John is the given first name of the 19th-century English theologian and social reformer Frederick Denison Maurice.
  • E. John
    John is the given name of Sir John Lennard-Jones, a pioneering British theoretical chemist known for his work on intermolecular forces and the Lennard-Jones potential.
  • 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: John
Triple: [John Marshall, givenName, John]
Generated description
John is the given name of John Marshall, the influential fourth Chief Justice of the United States who helped define the role of the Supreme Court and the development of American constitutional law.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given name of John Marshall, the influential fourth Chief Justice of the United States who helped define the role of the Supreme Court and the development of American constitutional law.
  • A. John
    John is the given name of John Jay, one of the Founding Fathers of the United States and the first Chief Justice of the U.S. Supreme Court.
  • B. John
    John is the given name of John Marshall Harlan, a prominent U.S. Supreme Court Justice known for his influential dissents in civil rights cases.
  • C. John
    John is the given name of John G. Roberts Jr., the Chief Justice of the United States Supreme Court.
  • D. John
    John is the given name of John M. Harlan II, an influential 20th-century Associate Justice of the United States Supreme Court known for his strong advocacy of judicial restraint and civil liberties.
  • E. John
    John is the given name of John Paul Stevens, a long-serving associate justice of the United States Supreme Court.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eba51f08190ac5d9de7fc89405a completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f4b693c81908fd324a5e92fc23c completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff612f54a48190a392a3712db4c907 completed May 9, 2026, 4:30 p.m.
NED2 Entity disambiguation (via description) batch_69ff61fbcad481908af89369458b23ca completed May 9, 2026, 4:34 p.m.
Created at: April 10, 2026, 4:14 a.m.