Triple
T31607305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government of the Cook Islands |
E806524
|
entity |
| Predicate | monarchTitleInState |
P120179
|
FINISHED |
| Object | King of New Zealand |
—
|
NE NERFINISHED |
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: King of New Zealand | Statement: [Government of the Cook Islands, monarchTitleInState, King of New Zealand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monarchTitleInState Context triple: [Government of the Cook Islands, monarchTitleInState, King of New Zealand]
-
A.
monarchTitleInProvince
Indicates that a monarch holds a specific royal title associated with a particular province or territorial subdivision.
-
B.
monarchTitleIn
chosen
Indicates that a particular monarch holds or held a specific royal title within a given political or territorial entity.
-
C.
headOfStateTitle
Indicates the official title held by the person who serves as the head of state of a country or political entity.
-
D.
monarchicTitleHolderOf
Indicates that one entity holds a monarchic title associated with another entity (such as a realm, position, or office).
-
E.
monarchTitleContext
Indicates the specific situational or historical context in which a monarch’s title is held, used, or recognized.
- 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_69f348d61f2081908cad94bc9ffbb671 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 30, 2026, 10:35 p.m.