Triple
T437076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milwaukee |
E10031
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object |
Cavalier Johnson
Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
|
E57505
|
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: Cavalier Johnson | Statement: [Milwaukee, hasMayor, Cavalier Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cavalier Johnson Context triple: [Milwaukee, hasMayor, Cavalier Johnson]
-
A.
Christopher Johnson
Christopher Johnson is an American businessman and member of the Johnson family who serves as a principal owner and executive of the New York Jets NFL franchise.
-
B.
Patrick Carr
Patrick Carr was one of the five colonists fatally wounded in the 1770 Boston Massacre, whose death helped inflame anti-British sentiment in the American colonies.
-
C.
Jules Irving
Jules Irving was an influential American theater director, producer, and co-founder of the San Francisco Actor's Workshop who later led New York's Lincoln Center Repertory Company.
-
D.
DeVon Harris
DeVon Harris is a songwriter best known for his work on the track "So High."
-
E.
Jamal Greene
Jamal Greene is a prominent American constitutional law scholar and professor known for his work on rights adjudication and the interpretation of the U.S. Constitution.
- 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: Cavalier Johnson Triple: [Milwaukee, hasMayor, Cavalier Johnson]
Generated description
Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cavalier Johnson Target entity description: Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
-
A.
Christopher Johnson
Christopher Johnson is an American businessman and member of the Johnson family who serves as a principal owner and executive of the New York Jets NFL franchise.
-
B.
Patrick Carr
Patrick Carr was one of the five colonists fatally wounded in the 1770 Boston Massacre, whose death helped inflame anti-British sentiment in the American colonies.
-
C.
Jules Irving
Jules Irving was an influential American theater director, producer, and co-founder of the San Francisco Actor's Workshop who later led New York's Lincoln Center Repertory Company.
-
D.
DeVon Harris
DeVon Harris is a songwriter best known for his work on the track "So High."
-
E.
Jamal Greene
Jamal Greene is a prominent American constitutional law scholar and professor known for his work on rights adjudication and the interpretation of the U.S. Constitution.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef0c97188190b62104cb639d4b60 |
completed | Feb. 28, 2026, 1:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a44f522acc81909d16527bd08e458d |
completed | March 1, 2026, 2:38 p.m. |
| NEDg | Description generation | batch_69a44fd970d881909ed3ae28debf4760 |
completed | March 1, 2026, 2:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4506c3d4881908eb97e489e4b9078 |
completed | March 1, 2026, 2:42 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.