Triple

T11488511
Position Surface form Disambiguated ID Type / Status
Subject Eckerd College E272343 entity
Predicate founder P104 FINISHED
Object John M. Bevan
John M. Bevan was an American educator best known for founding Eckerd College in Florida.
 E1283014 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: John M. Bevan | Statement: [Eckerd College, founder, John M. Bevan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John M. Bevan
Context triple: [Eckerd College, founder, John M. Bevan]
  • A. James A. Beaver
    James A. Beaver was a 19th-century American politician and Civil War general who served as governor of Pennsylvania.
  • B. John B. Gough
    John B. Gough was a 19th-century American orator and reformer renowned for his powerful speeches advocating abstinence from alcohol and promoting the temperance cause.
  • C. Samuel E. Beetley
    Samuel E. Beetley was a film editor best known for his work on the epic World War II film "The Longest Day."
  • D. James M. McHaney
    James M. McHaney was an American lawyer who served as a chief prosecutor in several post-World War II Nuremberg war crimes trials.
  • E. Benjamin F. Blodgett
    Benjamin F. Blodgett is an individual notable enough to be specifically cited as a bearer of the Blodgett surname, though detailed public information about his life or achievements appears limited.
  • 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: John M. Bevan
Triple: [Eckerd College, founder, John M. Bevan]
Generated description
John M. Bevan was an American educator best known for founding Eckerd College in Florida.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John M. Bevan
Target entity description: John M. Bevan was an American educator best known for founding Eckerd College in Florida.
  • A. James A. Beaver
    James A. Beaver was a 19th-century American politician and Civil War general who served as governor of Pennsylvania.
  • B. John B. Gough
    John B. Gough was a 19th-century American orator and reformer renowned for his powerful speeches advocating abstinence from alcohol and promoting the temperance cause.
  • C. Samuel E. Beetley
    Samuel E. Beetley was a film editor best known for his work on the epic World War II film "The Longest Day."
  • D. James M. McHaney
    James M. McHaney was an American lawyer who served as a chief prosecutor in several post-World War II Nuremberg war crimes trials.
  • E. Benjamin F. Blodgett
    Benjamin F. Blodgett is an individual notable enough to be specifically cited as a bearer of the Blodgett surname, though detailed public information about his life or achievements appears limited.
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85a20df608190992543b4d7006f8a completed April 10, 2026, 2:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a022308f26081909d9c77d8327fee8e completed May 11, 2026, 6:42 p.m.
NEDg Description generation batch_6a0227c9e3408190ad559cd97919235d completed May 11, 2026, 7:02 p.m.
NED2 Entity disambiguation (via description) batch_6a02282bb2748190ad51b83c240cc429 completed May 11, 2026, 7:04 p.m.
Created at: April 8, 2026, 9:36 p.m.