Triple

T1522224
Position Surface form Disambiguated ID Type / Status
Subject Karen people E32254 entity
Predicate language P15 FINISHED
Object Pa’O language
The Pa’O language is a Tibeto-Burman language spoken primarily by the Pa’O (Taungthu) people of Myanmar, especially in Shan and Kayin States.
 E179082 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: Pa’O language | Statement: [Karen people, language, Pa’O language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pa’O language
Context triple: [Karen people, language, Pa’O language]
  • A. Tonsawang language
    Tonsawang language is an Austronesian language spoken by the Tonsawang people in North Sulawesi, Indonesia, and is part of the Minahasan subgroup.
  • B. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • C. Kalao language
    The Kalao language is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • D. Achuar-Shiwiar language
    The Achuar-Shiwiar language is a Jivaroan language spoken by the Achuar and Shiwiar Indigenous peoples of the Amazon rainforest in Ecuador and Peru.
  • E. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern 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: Pa’O language
Triple: [Karen people, language, Pa’O language]
Generated description
The Pa’O language is a Tibeto-Burman language spoken primarily by the Pa’O (Taungthu) people of Myanmar, especially in Shan and Kayin States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pa’O language
Target entity description: The Pa’O language is a Tibeto-Burman language spoken primarily by the Pa’O (Taungthu) people of Myanmar, especially in Shan and Kayin States.
  • A. Tonsawang language
    Tonsawang language is an Austronesian language spoken by the Tonsawang people in North Sulawesi, Indonesia, and is part of the Minahasan subgroup.
  • B. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • C. Kalao language
    The Kalao language is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • D. Achuar-Shiwiar language
    The Achuar-Shiwiar language is a Jivaroan language spoken by the Achuar and Shiwiar Indigenous peoples of the Amazon rainforest in Ecuador and Peru.
  • E. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern 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_69a885e9b0ac819093a9806ad0efc82c completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a907fe8b0c8190a765afd3a10ee5e0 completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad401616ec81908edd9dcb9f4a0184 completed March 8, 2026, 9:23 a.m.
NEDg Description generation batch_69ad4130bf30819092be42a4e9225220 completed March 8, 2026, 9:28 a.m.
NED2 Entity disambiguation (via description) batch_69ad41968e4c8190b843b97e18ac9968 completed March 8, 2026, 9:29 a.m.
Created at: March 4, 2026, 7:26 p.m.