Triple

T13068702
Position Surface form Disambiguated ID Type / Status
Subject Mark Sanford E329396 entity
Predicate familyName P18 FINISHED
Object Sanford
Sanford is a surname of English origin borne by various notable individuals, including American politician Mark Sanford.
E670617 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: Sanford | Statement: [Mark Sanford, familyName, Sanford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanford
Context triple: [Mark Sanford, familyName, Sanford]
  • A. Sanford
    Sanford is the given first name of legendary American Major League Baseball pitcher Sandy Koufax.
  • B. Sanford
    Sanford is a major American manufacturer of writing instruments, best known as the parent company behind brands like Sharpie and Paper Mate.
  • C. Sanford
    Sanford is a small rural town located in Conejos County in southern Colorado, known for its agricultural surroundings and close-knit community.
  • D. Sanford
    Sanford is a classic American television sitcom best known for its sharp-tongued humor and portrayal of a cantankerous junk dealer and his family in Los Angeles.
  • E. Sanford
    Sanford is a small town located in Covington County in the southern part of the U.S. state of Alabama.
  • 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: Sanford
Triple: [Mark Sanford, familyName, Sanford]
Generated description
Sanford is a surname of English origin borne by various notable individuals, including American politician Mark Sanford.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sanford
Target entity description: Sanford is a surname of English origin borne by various notable individuals, including American politician Mark Sanford.
  • A. Sanford
    Sanford is an American philanthropist and businessman best known for his major charitable contributions to healthcare and education institutions.
  • B. Sanford
    Sanford is the given first name of legendary American Major League Baseball pitcher Sandy Koufax.
  • C. Sanford chosen
    Sanford is a surname most notably associated with American actress Isabel Sanford, famed for her role as Louise "Weezy" Jefferson on the sitcom The Jeffersons.
  • D. Sanford
    Sanford is a major American manufacturer of writing instruments, best known as the parent company behind brands like Sharpie and Paper Mate.
  • E. Sanford
    Sanford is a city in central North Carolina that serves as a regional hub for education, industry, and commerce.
  • 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_69d80771749c81909a6d9197b9504872 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980ec8ba48190baf52c7823482680 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d603419c8190b8d1726365db59dc completed May 3, 2026, 4:58 a.m.
NEDg Description generation batch_69f6d943a80c81909bc39b9a9ef303bd completed May 3, 2026, 5:12 a.m.
NED2 Entity disambiguation (via description) batch_69f6da1e56388190b536831b2c6d493f completed May 3, 2026, 5:16 a.m.
Created at: April 9, 2026, 9 p.m.