Triple

T6753828
Position Surface form Disambiguated ID Type / Status
Subject Cornell College E154402 entity
Predicate president P8 FINISHED
Object Jonathan Brand
Jonathan Brand is an American academic administrator and lawyer who serves as the president of Cornell College in Mount Vernon, Iowa.
E621248 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: Jonathan Brand | Statement: [Cornell College, president, Jonathan Brand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jonathan Brand
Context triple: [Cornell College, president, Jonathan Brand]
  • A. Joe Brandt
    Joe Brandt was an American film industry executive and producer best known as one of the co-founders of Columbia Pictures.
  • B. Mark Brandenburg
    Mark Brandenburg is a historic region in northeastern Germany that formed the core of the medieval Margraviate of Brandenburg and later became central to the rise of Prussia.
  • C. Joshua Brand
    Joshua Brand is an American television writer and producer best known for co-creating acclaimed series such as *St. Elsewhere* and *Northern Exposure*.
  • D. Michael Bradsell
    Michael Bradsell is a British science fiction editor best known for his work on the magazine Jabberwocky.
  • E. Michael Bradsell
    Michael Bradsell is a British film editor known for his work on notable films including Kenneth Branagh’s adaptation of "Henry V" (1989).
  • 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: Jonathan Brand
Triple: [Cornell College, president, Jonathan Brand]
Generated description
Jonathan Brand is an American academic administrator and lawyer who serves as the president of Cornell College in Mount Vernon, Iowa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jonathan Brand
Target entity description: Jonathan Brand is an American academic administrator and lawyer who serves as the president of Cornell College in Mount Vernon, Iowa.
  • A. Joe Brandt
    Joe Brandt was an American film industry executive and producer best known as one of the co-founders of Columbia Pictures.
  • B. Mark Brandenburg
    Mark Brandenburg is a historic region in northeastern Germany that formed the core of the medieval Margraviate of Brandenburg and later became central to the rise of Prussia.
  • C. Joshua Brand
    Joshua Brand is an American television writer and producer best known for co-creating acclaimed series such as *St. Elsewhere* and *Northern Exposure*.
  • D. Michael Bradsell
    Michael Bradsell is a British film editor known for his work on notable films including Kenneth Branagh’s adaptation of "Henry V" (1989).
  • E. Michael Bradsell
    Michael Bradsell is a British science fiction editor best known for his work on the magazine Jabberwocky.
  • 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_69c6880fd5808190be684854081e27dd completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1f32fa08190bb23dc24fef14c8d completed March 27, 2026, 6:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723c3eb4881909c9c8d1258f461d9 completed March 28, 2026, 12:41 a.m.
NEDg Description generation batch_69c7249209b88190a50fa7b96dd88b10 completed March 28, 2026, 12:45 a.m.
NED2 Entity disambiguation (via description) batch_69c7250865808190a1d20e8fe6f9de49 completed March 28, 2026, 12:47 a.m.
Created at: March 27, 2026, 2:11 p.m.