Triple

T17549177
Position Surface form Disambiguated ID Type / Status
Subject John Gregg Fee E427410 entity
Predicate familyName P18 FINISHED
Object Fee
Fee is a surname most notably associated with John Gregg Fee, an American abolitionist and co-founder of Berea College in Kentucky.
 E1275744 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: Fee | Statement: [John Gregg Fee, familyName, Fee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fee
Context triple: [John Gregg Fee, familyName, Fee]
  • A. FEES
    FEES is Chile’s sovereign wealth fund designed to stabilize the country’s public finances by saving and investing surplus fiscal revenues, particularly from copper exports.
  • B. Finder's Fee
    Finder's Fee is a 2001 independent thriller film centered on a high-stakes moral dilemma after a man discovers a winning lottery ticket during a poker night.
  • C. COST
    COST is the stock ticker symbol for Costco Wholesale Corporation, a major American membership-based warehouse retail chain.
  • D. kal-if-fee
    Kal-if-fee is a traditional Vulcan ritual combat to the death used to resolve mating disputes in the Star Trek universe.
  • E. FeeX
    FeeX is a financial technology company that helps consumers identify and reduce hidden fees in their investment and retirement accounts.
  • 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: Fee
Triple: [John Gregg Fee, familyName, Fee]
Generated description
Fee is a surname most notably associated with John Gregg Fee, an American abolitionist and co-founder of Berea College in Kentucky.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fee
Target entity description: Fee is a surname most notably associated with John Gregg Fee, an American abolitionist and co-founder of Berea College in Kentucky.
  • A. FEES
    FEES is Chile’s sovereign wealth fund designed to stabilize the country’s public finances by saving and investing surplus fiscal revenues, particularly from copper exports.
  • B. Finder's Fee
    Finder's Fee is a 2001 independent thriller film centered on a high-stakes moral dilemma after a man discovers a winning lottery ticket during a poker night.
  • C. COST
    COST is the stock ticker symbol for Costco Wholesale Corporation, a major American membership-based warehouse retail chain.
  • D. kal-if-fee
    Kal-if-fee is a traditional Vulcan ritual combat to the death used to resolve mating disputes in the Star Trek universe.
  • E. FeeX
    FeeX is a financial technology company that helps consumers identify and reduce hidden fees in their investment and retirement accounts.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e45463ddf88190a2c29f3246adcb6e completed April 19, 2026, 4:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01d28f01588190b608e9e8c6c63635 completed May 11, 2026, 12:58 p.m.
NEDg Description generation batch_6a01d39bf344819096a89179137e22ab completed May 11, 2026, 1:03 p.m.
NED2 Entity disambiguation (via description) batch_6a01d48da4b0819094d4e32847b97345 completed May 11, 2026, 1:07 p.m.
Created at: April 10, 2026, 5:49 a.m.