Triple
T17934737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deputy Prime Minister of New Zealand |
E448429
|
entity |
| Predicate | currentHolderAssumedOfficeYear |
P61436
|
FINISHED |
| Object | 2023 |
—
|
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: 2023 | Statement: [Deputy Prime Minister of New Zealand, currentHolderAssumedOfficeYear, 2023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentHolderAssumedOfficeYear Context triple: [Deputy Prime Minister of New Zealand, currentHolderAssumedOfficeYear, 2023]
-
A.
currentIncumbentStartYear
chosen
Indicates the year in which the entity’s current incumbent began their tenure or term in that role.
-
B.
currentSpeakerAssumedOffice
Indicates that the person who is currently serving as speaker has taken up or begun holding a particular office or position.
-
C.
lastOfficeHolderStartDate
Indicates the date on which the most recent person to hold a particular office or position began their term.
-
D.
officeHolderAsOf
Indicates that a person holds or held a specific office or position as of a particular date or point in time.
-
E.
inauguralHolderYear
Indicates the year in which the first holder or occupant of a position, title, or role began their tenure.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a55536e0819083dcfc4be71d447a |
completed | April 19, 2026, 9:50 a.m. |
| PD | Predicate disambiguation | batch_69e3f8e713d481908b4a126258c18b63 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.