Triple

T14071782
Position Surface form Disambiguated ID Type / Status
Subject J. Parnell Thomas E338625 entity
Predicate givenName P17 FINISHED
Object John
John is the given first name of J. Parnell Thomas, an American politician who served as a U.S. Representative from New Jersey and chaired the House Un-American Activities Committee.
E1083644 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: [J. Parnell Thomas, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [J. Parnell Thomas, givenName, John]
  • A. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • B. John
    John Ross is a personal name shared by various notable individuals across history, including leaders, politicians, and public figures.
  • C. John
    John of Görlitz was a 14th-century German prince of the House of Luxembourg who held the title of Duke of Görlitz.
  • D. John
    John is the given name of John C. Sheehan, an American organic chemist renowned for achieving the first complete laboratory synthesis of penicillin.
  • E. John
    John is the first name of Jack Phillips, the British wireless operator on the RMS Titanic who died during its sinking in 1912.
  • 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: [J. Parnell Thomas, givenName, John]
Generated description
John is the given first name of J. Parnell Thomas, an American politician who served as a U.S. Representative from New Jersey and chaired the House Un-American Activities Committee.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given first name of J. Parnell Thomas, an American politician who served as a U.S. Representative from New Jersey and chaired the House Un-American Activities Committee.
  • A. John
    John is the first name of Dennis Hastert, the former Speaker of the United States House of Representatives.
  • B. John
    John is the given name of John Boehner, the American politician who served as the 53rd Speaker of the United States House of Representatives.
  • C. John
    John is the given name of John Joseph Moakley, a long-serving U.S. Congressman from Massachusetts.
  • D. John
    John is the first name of Jeremy Thorpe, a prominent British Liberal Party politician and former party leader.
  • E. John
    John is the given name of John Edward Fogarty, an American politician who served as a U.S. Representative from Rhode Island.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5c5aa828819098ef55a70a0decbc completed April 14, 2026, 3:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7d863ac819085bf5cd76cb2e8dd completed May 7, 2026, 8:36 p.m.
NEDg Description generation batch_69fd0070ded48190a2cd1a1f95a48d13 completed May 7, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_69fd012728788190b45639644e83afee completed May 7, 2026, 9:16 p.m.
Created at: April 9, 2026, 10:21 p.m.