Triple
T18003304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eva Aariak |
E430680
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Eva Aariak |
—
|
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: Eva Aariak | Statement: [Eva Aariak, name, Eva Aariak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eva Aariak Context triple: [Eva Aariak, name, Eva Aariak]
-
A.
Eva Aariak
chosen
Eva Aariak is a Canadian Inuk politician and former premier of Nunavut who has played a prominent role in the territory’s governance and promotion of Inuit language and culture.
-
B.
Helen Maksagak
Helen Maksagak was a pioneering Inuit politician who became the first Commissioner of Nunavut and the first woman and Inuk to serve as a territorial commissioner in Canada.
-
C.
Evy Scotvold
Evy Scotvold is an American figure skating coach best known for guiding Olympic medalist Nancy Kerrigan during her competitive career.
-
D.
Nina Jack
Nina Jack is a television producer known for her work on high-profile series including the sci-fi drama "Silo."
-
E.
Maya Hansen
Maya Hansen is a brilliant botanist and geneticist in the Marvel Cinematic Universe whose Extremis research plays a pivotal role in the events of Iron Man 3.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b3ea60608190b977644e946407b7 |
completed | April 19, 2026, 10:52 a.m. |
Created at: April 10, 2026, 10:23 a.m.