Triple
T9559428
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cook Islander |
E230628
|
entity |
| Predicate | collectiveDemonymFor |
P21261
|
FINISHED |
| Object | people of Rarotonga |
—
|
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: people of Rarotonga | Statement: [Cook Islander, collectiveDemonymFor, people of Rarotonga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectiveDemonymFor Context triple: [Cook Islander, collectiveDemonymFor, people of Rarotonga]
-
A.
relatedDemonym
Indicates that one entity is the demonym (name for residents or natives) associated with the other entity.
-
B.
populationDemonym
chosen
Indicates the term used to refer to the people or inhabitants associated with a particular place or region.
-
C.
hasDemonym
Indicates that one entity is the term (demonym) used to refer to the inhabitants or natives of another entity (typically a place).
-
D.
supporterDemonym
Indicates the relationship between an entity and the demonym used to refer to its supporters or fans.
-
E.
ethnicEponymOf
Indicates that one term is an eponym derived from or naming an ethnic group or people.
- 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_69ca847e53a88190a60eed7e02257f10 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd994a7e9c8190b68883c2ea45aa1a |
completed | April 1, 2026, 10:16 p.m. |
| PD | Predicate disambiguation | batch_69ccd594d0ac8190a81bc11a3a538167 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:03 p.m.