Triple
T24937491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jennifer Granholm |
E623355
|
entity |
| Predicate | officeStartTime (Attorney General of Michigan) |
P161428
|
FINISHED |
| Object | 1999-01-01 |
—
|
LITERAL FINISHED |
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: 1999-01-01 | Statement: [Jennifer Granholm, officeStartTime (Attorney General of Michigan), 1999-01-01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartTime (Attorney General of Michigan) Context triple: [Jennifer Granholm, officeStartTime (Attorney General of Michigan), 1999-01-01]
-
A.
officeStartTime (Governor of Michigan)
Indicates the time at which the Governor of Michigan officially begins their term in office.
-
B.
officeStartTime (U.S. Attorney General)
Indicates the time at which the U.S. Attorney General officially begins their term in office.
-
C.
officeStartTime (Attorney General of Arizona)
Indicates the time at which the Attorney General of Arizona officially begins their term in office.
-
D.
officeStartTime (Associate Justice)
Indicates the date and time at which an Associate Justice officially begins their term in office.
-
E.
officeEndTime (Governor of Michigan)
Indicates the time at which the Governor of Michigan’s term in office concludes.
- F. None of above. chosen
Provenance (4 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_69f613bc641c819084343cc78d080640 |
completed | May 2, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69f611a72780819082f44e66ca2c6ac9 |
completed | May 2, 2026, 3 p.m. |
| PDg | Predicate description generation | batch_69f613502d808190b89927e5e734b43a |
completed | May 2, 2026, 3:08 p.m. |
Created at: April 18, 2026, 5:30 a.m.