Triple
T25964643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol Moseley Braun |
E645631
|
entity |
| Predicate | officeStartTime (Ambassador to Samoa) |
P177092
|
FINISHED |
| Object | 1999 |
—
|
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 | Statement: [Carol Moseley Braun, officeStartTime (Ambassador to Samoa), 1999]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartTime (Ambassador to Samoa) Context triple: [Carol Moseley Braun, officeStartTime (Ambassador to Samoa), 1999]
-
A.
officeStartTime (Ambassador to New Zealand)
Indicates the date and time when an individual began serving as Ambassador to New Zealand.
-
B.
officeStartTime (Secretary of Commerce)
Indicates the date and time at which a person begins serving in the role of Secretary of Commerce.
-
C.
officeEndTime (Ambassador to New Zealand)
Indicates the time at which an individual's term as Ambassador to New Zealand officially concludes.
-
D.
officeStartTime (Archivist of the United States)
Indicates the time at which the Archivist of the United States officially begins their term in office.
-
E.
officeStartTime (Governor-General of Tuvalu)
Indicates the time at which the Governor-General of Tuvalu officially begins their term in office.
- 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_69e77e85efc08190997da7fcf98bd300 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69f6f854486c81909396d944a55e03ab |
completed | May 3, 2026, 7:25 a.m. |
Created at: April 22, 2026, 8:48 a.m.