Triple

T559843
Position Surface form Disambiguated ID Type / Status
Subject Joe Fulks E13424 entity
Predicate familyName P18 FINISHED
Object Fulks
Fulks is a surname most notably associated with early professional basketball star Joe Fulks, a pioneering scorer in the Basketball Association of America.
 E70227 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: Fulks | Statement: [Joe Fulks, familyName, Fulks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fulks
Context triple: [Joe Fulks, familyName, Fulks]
  • A. Svans
    Svans are a distinct subethnic group of Georgians known for their unique Svan language, highland culture, and traditional communities in the Svaneti region of the Caucasus.
  • B. Blatch
    Blatch is the surname of Nora Stanton Blatch, an early 20th-century American civil engineer, suffragist, and women's rights activist.
  • C. Mackmen
    The Mackmen was a nickname for the early 20th-century Philadelphia Athletics baseball team, derived from their legendary manager Connie Mack.
  • D. Ficker
    Ficker is the birth surname of renowned American ballerina Suzanne Farrell, one of the most celebrated muses of choreographer George Balanchine.
  • E. Ellies
    The Ellies are annual awards recognizing excellence in magazine journalism and publishing, presented by the American Society of Magazine Editors.
  • 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: Fulks
Triple: [Joe Fulks, familyName, Fulks]
Generated description
Fulks is a surname most notably associated with early professional basketball star Joe Fulks, a pioneering scorer in the Basketball Association of America.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fulks
Target entity description: Fulks is a surname most notably associated with early professional basketball star Joe Fulks, a pioneering scorer in the Basketball Association of America.
  • A. Svans
    Svans are a distinct subethnic group of Georgians known for their unique Svan language, highland culture, and traditional communities in the Svaneti region of the Caucasus.
  • B. Blatch
    Blatch is the surname of Nora Stanton Blatch, an early 20th-century American civil engineer, suffragist, and women's rights activist.
  • C. Mackmen
    The Mackmen was a nickname for the early 20th-century Philadelphia Athletics baseball team, derived from their legendary manager Connie Mack.
  • D. Ficker
    Ficker is the birth surname of renowned American ballerina Suzanne Farrell, one of the most celebrated muses of choreographer George Balanchine.
  • E. Ellies
    The Ellies are annual awards recognizing excellence in magazine journalism and publishing, presented by the American Society of Magazine Editors.
  • 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_69a4933edcf08190b35ecfd6014caee6 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a499e13694819087a236bffa6601a9 completed March 1, 2026, 7:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4e9bd6c44819094ba815966ca7937 completed March 2, 2026, 1:37 a.m.
NEDg Description generation batch_69a4ea332c2081909a615287ad0629be completed March 2, 2026, 1:38 a.m.
NED2 Entity disambiguation (via description) batch_69a4eadfefec81908fc3c2522fe79969 completed March 2, 2026, 1:41 a.m.
Created at: March 1, 2026, 7:32 p.m.