Triple

T8366303
Position Surface form Disambiguated ID Type / Status
Subject Hani E197135 entity
Predicate speaks P741 FINISHED
Object Hani language
The Hani language is a Tibeto-Burman language spoken primarily by the Hani people in southwestern China and neighboring regions of Southeast Asia.
 E728085 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: Hani language | Statement: [Hani, speaks, Hani language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hani language
Context triple: [Hani, speaks, Hani language]
  • A. Hanis language
    The Hanis language is an endangered Native American language traditionally spoken by the Coos people of the southern Oregon coast.
  • B. Hu language
    Hu language is a variety of Wu Chinese spoken primarily in and around Shanghai, known for its distinct phonology and vocabulary compared to Standard Mandarin.
  • C. Haliti language
    The Haliti language, also known as Paresí, is an Arawakan indigenous language spoken by the Paresí (Haliti) people of Brazil’s Mato Grosso region.
  • D. Hezhen language
    The Hezhen language is a critically endangered Tungusic language spoken by the Hezhen (Nanai) people of northeastern China along the Amur and Ussuri rivers.
  • E. Ahanta language
    The Ahanta language is a Niger-Congo language spoken by the Ahanta people along the coastal region of southwestern Ghana.
  • 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: Hani language
Triple: [Hani, speaks, Hani language]
Generated description
The Hani language is a Tibeto-Burman language spoken primarily by the Hani people in southwestern China and neighboring regions of Southeast Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hani language
Target entity description: The Hani language is a Tibeto-Burman language spoken primarily by the Hani people in southwestern China and neighboring regions of Southeast Asia.
  • A. Hanis language
    The Hanis language is an endangered Native American language traditionally spoken by the Coos people of the southern Oregon coast.
  • B. Hu language
    Hu language is a variety of Wu Chinese spoken primarily in and around Shanghai, known for its distinct phonology and vocabulary compared to Standard Mandarin.
  • C. Haliti language
    The Haliti language, also known as Paresí, is an Arawakan indigenous language spoken by the Paresí (Haliti) people of Brazil’s Mato Grosso region.
  • D. Hezhen language
    The Hezhen language is a critically endangered Tungusic language spoken by the Hezhen (Nanai) people of northeastern China along the Amur and Ussuri rivers.
  • E. Ahanta language
    The Ahanta language is a Niger-Congo language spoken by the Ahanta people along the coastal region of southwestern Ghana.
  • 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_69ca82f2dbe48190aba982e75a0d94de completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb808cf80c8190941c3cc0248a5df2 completed March 31, 2026, 8:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc78c0c208190ba590c74512a4043 completed April 2, 2026, 1:34 a.m.
NEDg Description generation batch_69cdcc88456c8190ba8613b4cbf40fbb completed April 2, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69cdcd75714881908f0b069a94ee334f completed April 2, 2026, 1:59 a.m.
Created at: March 30, 2026, 6 p.m.