Triple
T4866322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kunama |
E108778
|
entity |
| Predicate | hasDialects |
P4251
|
FINISHED |
| Object | Ilit Kunama |
E108778
|
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: Ilit Kunama | Statement: [Kunama, hasDialects, Ilit Kunama]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ilit Kunama Context triple: [Kunama, hasDialects, Ilit Kunama]
-
A.
Manjil
Manjil is a town in northern Iran known for its strong winds and wind farms, situated in the mountainous region of Gilan Province.
-
B.
Iya Labunka
Iya Labunka is a film producer known for her work on genre films, including serving as a producer on the horror sequel "Scream 4."
-
C.
Kunama
chosen
Kunama is a Nilo-Saharan language spoken primarily by the Kunama people in western Eritrea and adjacent parts of Ethiopia.
-
D.
Kala Lagaw Ya
Kala Lagaw Ya is an Australian Aboriginal language of the Western Torres Strait, spoken by Torres Strait Islanders and known for its complex grammar and long-standing contact with Papuan and Austronesian languages.
-
E.
Kulitan
Kulitan is the indigenous precolonial script used to write the Kapampangan language of the Philippines.
- 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_69bd440b965081908b0557721cae6338 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d7a42f88190bb1ef7261bcbc2a8 |
completed | March 20, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be67e5d96c8190b2a509d9fb81211a |
completed | March 21, 2026, 9:41 a.m. |
Created at: March 20, 2026, 1:26 p.m.