Triple
T1455775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edmund Muskie |
E31395
|
entity |
| Predicate | startTime (U.S. Secretary of State) |
P28808
|
FINISHED |
| Object | 1980 |
—
|
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: 1980 | Statement: [Edmund Muskie, startTime (U.S. Secretary of State), 1980]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime (U.S. Secretary of State) Context triple: [Edmund Muskie, startTime (U.S. Secretary of State), 1980]
-
A.
startTime (Governor of New Jersey)
Indicates the point in time at which a person begins serving as Governor of New Jersey.
-
B.
startTime (Governor of South Carolina)
Indicates the point in time at which a person begins serving as Governor of South Carolina.
-
C.
startTime (Director of OMB)
Indicates the point in time at which a person begins serving as Director of the Office of Management and Budget.
-
D.
startTime (Minister to the UK)
Indicates the date and time at which the person began serving in the role of Minister to the UK.
-
E.
succeededInOfficeAsSecretaryOfStateBy
Indicates that one individual was followed in the role of Secretary of State by another individual, who took over the office after them.
- 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_69a499171a28819085b993a3ac78e363 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c581714881909bf4c2bad9645176 |
completed | March 1, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69a4c47cdbd0819092022344a2f4ad7b |
completed | March 1, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69a4c55508948190922aee3230a4323e |
completed | March 1, 2026, 11:01 p.m. |
Created at: March 1, 2026, 8 p.m.