Triple
T23104101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Leon Brewer |
E576113
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jan Brewer |
—
|
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: Jan Brewer | Statement: [John Leon Brewer, spouse, Jan Brewer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Brewer Context triple: [John Leon Brewer, spouse, Jan Brewer]
-
A.
Jan Brewer
chosen
Jan Brewer is an American Republican politician who served as the 22nd governor of Arizona from 2009 to 2015.
-
B.
Mark Brnovich
Mark Brnovich is an American attorney and Republican politician who served as the Attorney General of Arizona.
-
C.
Doug Ducey (as Governor of Arizona)
Doug Ducey is a Republican politician and former Cold Stone Creamery CEO who served as the 23rd governor of Arizona from 2015 to 2023.
-
D.
Katie Hobbs
Katie Hobbs is an American politician and member of the Democratic Party who serves as the governor of Arizona and previously held statewide office as secretary of state.
-
E.
Mary Fallin
Mary Fallin is an American Republican politician who served as the first female governor of Oklahoma.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18deb702c819099f2e2141706f00e |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.