Triple

T1002298
Position Surface form Disambiguated ID Type / Status
Subject John Sullivan E21630 entity
Predicate familyName P18 FINISHED
Object Sullivan
Sullivan is a common Irish-origin surname borne by numerous notable figures across politics, sports, entertainment, and other fields.
 E29832 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: Sullivan | Statement: [John Sullivan, familyName, Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sullivan
Context triple: [John Sullivan, familyName, Sullivan]
  • A. Sullivan
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • B. Dolan
    Dolan is a surname most prominently associated with the American business family that controls Madison Square Garden Sports and Entertainment, including executive James L. Dolan.
  • C. Willis
    Willis is a masculine given name and surname of English origin, often considered a variant or cognate of the name Wilson.
  • D. Rawson
    Rawson is a coastal city in southern Argentina that serves as the capital of Chubut Province and an important administrative and fishing center in Patagonia.
  • E. Riggs
    Riggs is a surname most notably associated with American playwright Lynn Riggs, whose work inspired the musical "Oklahoma!".
  • 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: Sullivan
Triple: [John Sullivan, familyName, Sullivan]
Generated description
Sullivan is a common Irish-origin surname borne by numerous notable figures across politics, sports, entertainment, and other fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sullivan
Target entity description: Sullivan is a common Irish-origin surname borne by numerous notable figures across politics, sports, entertainment, and other fields.
  • A. Sullivan chosen
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • B. Dolan
    Dolan is a surname most prominently associated with the American business family that controls Madison Square Garden Sports and Entertainment, including executive James L. Dolan.
  • C. Willis
    Willis is a masculine given name and surname of English origin, often considered a variant or cognate of the name Wilson.
  • D. Rawson
    Rawson is a coastal city in southern Argentina that serves as the capital of Chubut Province and an important administrative and fishing center in Patagonia.
  • E. Riggs
    Riggs is a surname most notably associated with American playwright Lynn Riggs, whose work inspired the musical "Oklahoma!".
  • 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_69a493c53e648190ae8cb76c433fd9a7 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4fcbc04819098d2125518f62ae7 completed March 1, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3ba7063c8190ba79e974cf38cdea completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3c41ab70819090084c508dbfd295 completed March 7, 2026, 2:54 p.m.
NED2 Entity disambiguation (via description) batch_69ac3cbb30d081909759df25c21eb275 completed March 7, 2026, 2:56 p.m.
Created at: March 1, 2026, 7:41 p.m.