Triple
T16311013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taneti Maamau |
E396053
|
entity |
| Predicate | termStartAsPresidentOfKiribati |
P14209
|
FINISHED |
| Object | 2016 |
—
|
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: 2016 | Statement: [Taneti Maamau, termStartAsPresidentOfKiribati, 2016]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termStartAsPresidentOfKiribati Context triple: [Taneti Maamau, termStartAsPresidentOfKiribati, 2016]
-
A.
startTimeAsHeadOfState
Indicates the date and time when an individual begins their tenure or service as a head of state.
-
B.
presidentTermStart
chosen
Indicates the date or point in time when an individual officially begins serving as president of an entity.
-
C.
termOfOfficeInaugurated
Indicates the event or date on which an individual officially begins their term of office through an inauguration.
-
D.
termAsActingPresidentStart
Indicates the date or point in time when an individual begins serving in the role of acting president.
-
E.
headOfGovernmentDuringTermStart
Indicates that a person serves as the head of government at the beginning of a specified political term.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288da27f88190aa241e3addf9cd7f |
completed | April 17, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.