Triple

T13145180
Position Surface form Disambiguated ID Type / Status
Subject New Irelanders E312316 entity
Predicate usesLanguage P238 FINISHED
Object Mandak language
The Mandak language is an Austronesian language spoken by communities on New Ireland in Papua New Guinea.
E1024257 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: Mandak language | Statement: [New Irelanders, usesLanguage, Mandak language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandak language
Context triple: [New Irelanders, usesLanguage, Mandak language]
  • A. Mandar language
    Mandar is an Austronesian language spoken primarily by the Mandar people along the western coast of Sulawesi in Indonesia.
  • B. Mandeali language
    Mandeali language is an Indo-Aryan language spoken primarily in the Mandi region of Himachal Pradesh, India.
  • C. Manda language
    The Manda language is a South-Central Dravidian language spoken by the Manda people in parts of eastern India, known for its endangered status and limited number of speakers.
  • D. Mankanya language
    The Mankanya language is an Atlantic language of the Niger-Congo family spoken primarily in parts of Guinea-Bissau, Senegal, and The Gambia by the Mankanya people.
  • E. Mundani language
    Mundani language is a Grassfields Bantu language spoken by the Mundani people in the Western Region of Cameroon.
  • 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: Mandak language
Triple: [New Irelanders, usesLanguage, Mandak language]
Generated description
The Mandak language is an Austronesian language spoken by communities on New Ireland in Papua New Guinea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mandak language
Target entity description: The Mandak language is an Austronesian language spoken by communities on New Ireland in Papua New Guinea.
  • A. Mandar language
    Mandar is an Austronesian language spoken primarily by the Mandar people along the western coast of Sulawesi in Indonesia.
  • B. Mandeali language
    Mandeali language is an Indo-Aryan language spoken primarily in the Mandi region of Himachal Pradesh, India.
  • C. Manda language
    The Manda language is a South-Central Dravidian language spoken by the Manda people in parts of eastern India, known for its endangered status and limited number of speakers.
  • D. Mankanya language
    The Mankanya language is an Atlantic language of the Niger-Congo family spoken primarily in parts of Guinea-Bissau, Senegal, and The Gambia by the Mankanya people.
  • E. Mundani language
    Mundani language is a Grassfields Bantu language spoken by the Mundani people in the Western Region of Cameroon.
  • 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98bcf6d0c819081d078f33e4bdedc completed April 10, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eae675508190991ce5902768c45a completed May 3, 2026, 6:27 a.m.
NEDg Description generation batch_69f6ebb1cd208190970ad8c21e852d93 completed May 3, 2026, 6:31 a.m.
NED2 Entity disambiguation (via description) batch_69f6ec48035881909342b57c061a22a9 completed May 3, 2026, 6:33 a.m.
Created at: April 9, 2026, 9:10 p.m.