Triple

T20170522
Position Surface form Disambiguated ID Type / Status
Subject Oroqen E491945 entity
Predicate traditionalLanguage P6149 FINISHED
Object Oroqen language
The Oroqen language is a critically endangered Tungusic language spoken by the Oroqen people of northeastern China and parts of Siberia.
 E1415346 NE FINISHED

How this triple was built (4 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: Oroqen language | Statement: [Oroqen, traditionalLanguage, Oroqen language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Oroqen language
Context triple: [Oroqen, traditionalLanguage, Oroqen language]
  • A. Oroqen dialect
    The Oroqen dialect is a regional variety of the Tungusic Evenki language spoken primarily by the Oroqen people of northeastern China.
  • B. Orok language
    The Orok language is a critically endangered Tungusic language spoken by the Orok (Uilta) people of Sakhalin Island in Russia.
  • C. 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.
  • D. Oro language
    The Oro language is the traditional indigenous language spoken by the Oro people of Papua New Guinea.
  • E. Nyoro language
    The Nyoro language is a Bantu language spoken primarily by the Banyoro people in western Uganda.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Oroqen language
Triple: [Oroqen, traditionalLanguage, Oroqen language]
Generated description
The Oroqen language is a critically endangered Tungusic language spoken by the Oroqen people of northeastern China and parts of Siberia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Oroqen language
Target entity description: The Oroqen language is a critically endangered Tungusic language spoken by the Oroqen people of northeastern China and parts of Siberia.
  • A. Oroqen dialect
    The Oroqen dialect is a regional variety of the Tungusic Evenki language spoken primarily by the Oroqen people of northeastern China.
  • B. Orok language
    The Orok language is a critically endangered Tungusic language spoken by the Orok (Uilta) people of Sakhalin Island in Russia.
  • C. 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.
  • D. Oro language
    The Oro language is the traditional indigenous language spoken by the Oro people of Papua New Guinea.
  • E. Nyoro language
    The Nyoro language is a Bantu language spoken primarily by the Banyoro people in western Uganda.
  • F. None of above. chosen

Provenance (5 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66847ed9481908e6b23b399fa7005 completed April 20, 2026, 5:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a083484eaa4819083462003ba5a78b0 completed May 16, 2026, 9:10 a.m.
NEDg Description generation batch_6a083851ccf081909de87d5070e969f9 completed May 16, 2026, 9:26 a.m.
NED2 Entity disambiguation (via description) batch_6a0838c3694c819097516c8de60864fb completed May 16, 2026, 9:28 a.m.
Created at: April 11, 2026, 11:35 p.m.