Triple

T9051611
Position Surface form Disambiguated ID Type / Status
Subject Bahnaric E216896 entity
Predicate hasLanguage P15 FINISHED
Object Jruʼ
Jruʼ is an Austroasiatic language spoken by the Jruʼ ethnic group, primarily in parts of Laos.
 E775494 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: Jruʼ | Statement: [Bahnaric, hasLanguage, Jruʼ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jruʼ
Context triple: [Bahnaric, hasLanguage, Jruʼ]
  • A. Xpujil
    Xpujil is a small town in the Mexican state of Campeche that serves as a key gateway to the nearby Calakmul Biosphere Reserve and its ancient Maya ruins.
  • B. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim dynasty.
  • C. Ráquira
    Ráquira is a Colombian town renowned for its traditional pottery, colorful handicrafts, and vibrant colonial architecture.
  • D. Juh
    Juh was a prominent Chiricahua Apache chief and war leader who played a key role in resisting U.S. and Mexican military forces during the Apache Wars.
  • E. Upurui
    Upurui is an alternative name for the Wayana language, an indigenous Cariban language spoken by the Wayana people in parts of Brazil, Suriname, and French Guiana.
  • 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: Jruʼ
Triple: [Bahnaric, hasLanguage, Jruʼ]
Generated description
Jruʼ is an Austroasiatic language spoken by the Jruʼ ethnic group, primarily in parts of Laos.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jruʼ
Target entity description: Jruʼ is an Austroasiatic language spoken by the Jruʼ ethnic group, primarily in parts of Laos.
  • A. Xpujil
    Xpujil is a small town in the Mexican state of Campeche that serves as a key gateway to the nearby Calakmul Biosphere Reserve and its ancient Maya ruins.
  • B. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim dynasty.
  • C. Ráquira
    Ráquira is a Colombian town renowned for its traditional pottery, colorful handicrafts, and vibrant colonial architecture.
  • D. Juh
    Juh was a prominent Chiricahua Apache chief and war leader who played a key role in resisting U.S. and Mexican military forces during the Apache Wars.
  • E. Upurui
    Upurui is an alternative name for the Wayana language, an indigenous Cariban language spoken by the Wayana people in parts of Brazil, Suriname, and French Guiana.
  • 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_69ca83d362e88190ae44b4e4dc194209 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc7a700de48190aa9f61d850e01cbd completed April 1, 2026, 1:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfebc90bf88190bbcdab07ca93f569 completed April 3, 2026, 4:33 p.m.
NEDg Description generation batch_69cfecf7fce08190a9b80044a2ae9745 completed April 3, 2026, 4:38 p.m.
NED2 Entity disambiguation (via description) batch_69cff0ea8c388190bd95233db9c69038 completed April 3, 2026, 4:55 p.m.
Created at: March 30, 2026, 7:10 p.m.