Triple

T14666187
Position Surface form Disambiguated ID Type / Status
Subject Beverly Franklin E344380 entity
Predicate hasSurname P18 FINISHED
Object Franklin
Franklin is a common English surname borne by numerous notable individuals across politics, science, and the arts.
E58775 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: Franklin | Statement: [Beverly Franklin, hasSurname, Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franklin
Context triple: [Beverly Franklin, hasSurname, Franklin]
  • A. Franklin
    Franklin McCain was an American civil rights activist best known as one of the Greensboro Four who led the 1960 Woolworth’s lunch counter sit-in in North Carolina.
  • B. Franklin
    Franklin is a town in Norfolk County, Massachusetts, serving as a terminus for the MBTA Commuter Rail system.
  • C. Franklin
    Franklin is a wealthy, hospitable landowner and one of the storytellers in Geoffrey Chaucer’s The Canterbury Tales, known for his focus on gentility and marital harmony.
  • D. Franklin
    Franklin is an independent city in southeastern Virginia known for its small-town character and historical ties to the regional lumber and paper industries.
  • E. Franklin
    Franklin is the middle name of William Franklin Graham Jr., better known as the American evangelist Billy Graham.
  • 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: Franklin
Triple: [Beverly Franklin, hasSurname, Franklin]
Generated description
Franklin is a common English surname borne by numerous notable individuals across politics, science, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Franklin
Target entity description: Franklin is a common English surname borne by numerous notable individuals across politics, science, and the arts.
  • A. Franklin chosen
    Franklin is a common English surname borne by numerous notable individuals across fields such as politics, science, and the arts.
  • B. Franklin
    Franklin is a given name commonly used as a masculine first or middle name in English-speaking countries, historically associated with figures such as U.S. statesman Benjamin Franklin.
  • C. Franklin
    Franklin is the middle name of American inventor and engineer Charles F. Kettering, known for his influential work in automotive and industrial innovation.
  • D. Franklin
    Franklin is the given name of Franklin D. Roosevelt, the 32nd president of the United States who led the country through the Great Depression and World War II.
  • E. Franklin
    Franklin is the given name of Franklin Ajaye, an American stand-up comedian and actor known for his distinctive laid-back delivery and influential comedy albums.
  • 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_69d822e283fc8190a0e4c235cf880052 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb54c69f8819080a37161deecfba8 completed April 14, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5e63e6c8190ba67776719f2ff0c completed May 8, 2026, 12:24 p.m.
NEDg Description generation batch_69fdda3510bc8190b12783ded11b5796 completed May 8, 2026, 12:42 p.m.
NED2 Entity disambiguation (via description) batch_69fddaa56f4c8190ba56af6a7a56a201 completed May 8, 2026, 12:44 p.m.
Created at: April 10, 2026, 1:27 a.m.