Triple
T2756732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Nance Garner |
E61118
|
entity |
| Predicate | officeStartAsVicePresident |
P10270
|
FINISHED |
| Object | 1933 |
—
|
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: 1933 | Statement: [John Nance Garner, officeStartAsVicePresident, 1933]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartAsVicePresident Context triple: [John Nance Garner, officeStartAsVicePresident, 1933]
-
A.
termStartAsVicePresident
chosen
Indicates that an entity begins its term in office holding the position of vice president.
-
B.
officeStartForPresident
Indicates the date or point in time when a person begins serving in the role of president.
-
C.
leftOfficeAsVicePresident
Indicates that an individual ceased holding the position of vice president, marking the end of their term in that office.
-
D.
officeStartAsPrimeMinister
Indicates the point in time when an individual begins their term serving in the role of prime minister.
-
E.
vicePresident
Indicates that one entity holds the role of second-in-command or deputy leader to another entity within an organizational or governmental hierarchy.
- 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_69ab4b7a85bc819094a349b84beb1f2c |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb8a292c8190ab3982434805241a |
completed | March 7, 2026, 8:02 a.m. |
| PD | Predicate disambiguation | batch_69abd82d005c81908a1ac7a1313c6d88 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:56 p.m.