Triple
T18253375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Conyers |
E437156
|
entity |
| Predicate | officeEndForU.S.RepresentativeFromMichigan |
P71790
|
FINISHED |
| Object | 2017-12-05 |
—
|
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: 2017-12-05 | Statement: [John Conyers, officeEndForU.S.RepresentativeFromMichigan, 2017-12-05]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEndForU.S.RepresentativeFromMichigan Context triple: [John Conyers, officeEndForU.S.RepresentativeFromMichigan, 2017-12-05]
-
A.
officeEndTime (U.S. Representative)
chosen
Indicates the time at which a U.S. Representative’s term in office concludes.
-
B.
termEndAsGovernorOfMichigan
Indicates the time or event at which an individual's service as Governor of Michigan comes to an end.
-
C.
endTime (chairperson of Michigan Republican Party)
Indicates the point in time at which a person’s role as chairperson of the Michigan Republican Party concludes.
-
D.
officeEndTime (SC House of Representatives)
Indicates the time at which a member’s term or service in the South Carolina House of Representatives ends.
-
E.
officeEndTime (United States Senator)
Indicates the time at which a United States Senator’s term in office concludes.
- F. None of above.
Provenance (3 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4fd82f81c81909ad4455954bd8caa |
completed | April 19, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69e44fcdee748190bae6fb76e0cb22f3 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:33 a.m.