Triple
T10980323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Elizabeth Alexander Hanford |
E259485
|
entity |
| Predicate | endTime (as U.S. senator from North Carolina) |
P69808
|
FINISHED |
| Object | 2009 |
—
|
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: 2009 | Statement: [Mary Elizabeth Alexander Hanford, endTime (as U.S. senator from North Carolina), 2009]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTime (as U.S. senator from North Carolina) Context triple: [Mary Elizabeth Alexander Hanford, endTime (as U.S. senator from North Carolina), 2009]
-
A.
endTime (Governor of Virginia)
Indicates the point in time at which an individual’s tenure as Governor of Virginia concludes.
-
B.
officeEndTime (Governor of North Carolina)
Indicates the time at which a Governor of North Carolina’s term in office concludes.
-
C.
endTimeAsUSSenator
chosen
Indicates the date and time at which an individual’s service as a U.S. Senator concludes.
-
D.
endTime (House Majority Leader)
Indicates the point in time at which a person’s tenure or service as House Majority Leader concludes.
-
E.
endTime (House Majority Whip)
Indicates the point in time at which the person’s tenure or service as House Majority Whip 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d772e97cf88190a65dab3ec4e5f7f3 |
completed | April 9, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69d72e9055908190b438f039574aaaaf |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.