Triple
T22989809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Cannon |
E572014
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Joe Cannon |
—
|
NE NERFINISHED |
How this triple was built (2 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: Joe Cannon | Statement: [Joe Cannon, name, Joe Cannon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Cannon Context triple: [Joe Cannon, name, Joe Cannon]
-
A.
Joe Cannon
chosen
Joe Cannon is a former American professional soccer goalkeeper best known as one of Major League Soccer’s top shot-stoppers in the 2000s.
-
B.
Samuel Blodgett
Samuel Blodgett was an American lawyer, financier, and real estate developer known for his role in early U.S. federal projects, including work associated with the First Bank of the United States and the planning of Washington, D.C.
-
C.
Thomas C. Platt
Thomas C. Platt was a powerful late-19th-century Republican political boss from New York, often called the "Easy Boss" for his behind-the-scenes control of state politics.
-
D.
John T. Corley
John T. Corley was a highly decorated U.S. Army officer renowned for his valor and leadership during World War II and the Korean War.
-
E.
George H. Brown
George H. Brown was a British film producer and screenwriter active in the mid-20th century, known for his work on several notable British films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ea55cc8190b64b722ce8c45b53 |
completed | April 29, 2026, 4:02 a.m. |
Created at: April 17, 2026, 3:49 p.m.