Triple
T19609245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orok (Uilta) |
E470685
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Orok language |
—
|
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: Orok language | Statement: [Orok (Uilta), language, Orok language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orok language Context triple: [Orok (Uilta), language, Orok language]
-
A.
Orok language
chosen
The Orok language is a critically endangered Tungusic language spoken by the Orok (Uilta) people of Sakhalin Island in Russia.
-
B.
Oron language
The Oron language is a Niger-Congo language spoken by the Oron people of southeastern Nigeria, particularly in coastal areas of Akwa Ibom State.
-
C.
Oro language
The Oro language is the traditional indigenous language spoken by the Oro people of Papua New Guinea.
-
D.
Oroch language
The Oroch language is a critically endangered Tungusic language of the Russian Far East, traditionally spoken by the Oroch people along the lower Amur and nearby coastal areas.
-
E.
Olrat language
The Olrat language is an Oceanic language spoken by a small community in the Banks Islands of northern Vanuatu.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640ca57a081909c05000fca52271f |
completed | April 20, 2026, 3:05 p.m. |
Created at: April 10, 2026, 1:43 p.m.