Triple

T2105289
Position Surface form Disambiguated ID Type / Status
Subject Hainan E37179 entity
Predicate localLanguage P1252 FINISHED
Object Li language
Li language is an Austroasiatic language (often classified within the Tai–Kadai family) spoken primarily by the Li ethnic group indigenous to China’s Hainan Island.
 E233743 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: Li language | Statement: [Hainan, localLanguage, Li language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Li language
Context triple: [Hainan, localLanguage, Li language]
  • A. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • B. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • C. Kayeli language
    The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
  • D. Semai language
    The Semai language is an Austroasiatic language spoken by the Semai people, an indigenous Orang Asli group in Peninsular Malaysia.
  • E. Luri language
    Luri language is a Southwestern Iranian language spoken primarily by the Lur people in western and southwestern Iran.
  • 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: Li language
Triple: [Hainan, localLanguage, Li language]
Generated description
Li language is an Austroasiatic language (often classified within the Tai–Kadai family) spoken primarily by the Li ethnic group indigenous to China’s Hainan Island.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Li language
Target entity description: Li language is an Austroasiatic language (often classified within the Tai–Kadai family) spoken primarily by the Li ethnic group indigenous to China’s Hainan Island.
  • A. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • B. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • C. Kayeli language
    The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
  • D. Semai language
    The Semai language is an Austroasiatic language spoken by the Semai people, an indigenous Orang Asli group in Peninsular Malaysia.
  • E. Luri language
    Luri language is a Southwestern Iranian language spoken primarily by the Lur people in western and southwestern Iran.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbadcd4a081909d60b9b241950335 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae306bee8881908c62306fb1f6aea1 completed March 9, 2026, 2:29 a.m.
NEDg Description generation batch_69ae30e1c7488190acd6d29c5ad10c33 completed March 9, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_69ae316398488190b9dd38145d5488b4 completed March 9, 2026, 2:33 a.m.
Created at: March 4, 2026, 7:43 p.m.