Triple
T12497857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martu people |
E298739
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Kiyajarra |
E983955
|
NE 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: Kiyajarra | Statement: [Martu people, language, Kiyajarra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kiyajarra Context triple: [Martu people, language, Kiyajarra]
-
A.
Kaxuyana
Kaxuyana is an indigenous language variety spoken by the Kaxuyana people of northern Brazil, closely related to other Cariban languages of the region.
-
B.
Ubajara
Ubajara is a small Brazilian municipality in the state of Ceará, known for its location in the Serra da Ibiapaba highlands and for the nearby Ubajara National Park with its caves and waterfalls.
-
C.
Kariyarra
chosen
Kariyarra is an Australian Aboriginal language traditionally spoken by the Kariyarra people of the Pilbara region in Western Australia.
-
D.
Kejiahua
Kejiahua is the Chinese name for the Hakka language, a Sinitic language spoken by the Hakka people across southern China and various overseas communities.
-
E.
Itaitinga
Itaitinga is a municipality in the state of Ceará in northeastern Brazil, located in the metropolitan region of Fortaleza.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94dfa98348190b9ac164ecdada6fe |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65eaabadc81908f8af6bc10ce3238 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 8, 2026, 9:57 p.m.