Triple

T24937498
Position Surface form Disambiguated ID Type / Status
Subject Jennifer Granholm E623355 entity
Predicate succeededBy (Attorney General of Michigan) P38396 FINISHED
Object Mike Cox
Mike Cox is an American lawyer and Republican politician who served as Michigan's Attorney General in the 2000s.
 E1657389 NE FINISHED

How this triple was built (3 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: Mike Cox | Statement: [Jennifer Granholm, succeededBy (Attorney General of Michigan), Mike Cox]
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: Mike Cox
Triple: [Jennifer Granholm, succeededBy (Attorney General of Michigan), Mike Cox]
Generated description
Mike Cox is an American lawyer and Republican politician who served as Michigan's Attorney General in the 2000s.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: succeededBy (Attorney General of Michigan)
Context triple: [Jennifer Granholm, succeededBy (Attorney General of Michigan), Mike Cox]
  • A. succeededBy (as Attorney General) chosen
    Indicates that one individual later held the position of Attorney General after another individual, directly following them in that office.
  • B. succeededBy (Governor of Michigan)
    Indicates that one individual directly follows another in holding the office of Governor of Michigan.
  • C. succeededBy (Solicitor General of the United States)
    Indicates that one individual later held the position of Solicitor General of the United States after another, directly following them in that office.
  • D. precededBy (as Attorney General)
    Indicates that one person previously held the position of Attorney General before another person.
  • E. succeededBy (Sixth Circuit)
    Indicates that one entity in the context of the Sixth Circuit comes after and replaces another in a sequence, such as in office, position, or role.
  • F. None of above.

Provenance (6 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_69e2fac6b5a48190a1c38857f00915a9 completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f5ffc74fa481909b4fe24a9337f9eb completed May 2, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a103340e9e8819095238a51efedf38e completed May 22, 2026, 10:43 a.m.
NEDg Description generation batch_6a1033eeacac81909e208f3b3e17190e completed May 22, 2026, 10:46 a.m.
NED2 Entity disambiguation (via description) batch_6a1034cf890881908bd25523cdb83586 completed May 22, 2026, 10:49 a.m.
PD Predicate disambiguation batch_69f5f7f99dc08190afcfb3bc4dfbec1d completed May 2, 2026, 1:11 p.m.
Created at: April 18, 2026, 5:30 a.m.