Triple

T2274243
Position Surface form Disambiguated ID Type / Status
Subject Lozi E50731 entity
Predicate influencedBy P9 FINISHED
Object Luyana
Luyana is a Bantu language of southwestern Africa that historically served as a prestige and source language for the development of the Lozi language.
 E252594 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: Luyana | Statement: [Lozi, influencedBy, Luyana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Luyana
Context triple: [Lozi, influencedBy, Luyana]
  • A. Tianeti
    Tianeti is a small town and administrative center in eastern Georgia, situated in the mountainous Mtskheta-Mtianeti region.
  • B. Yanaon
    Yanaon is the former name of Yanam, a small coastal town in India that was once part of French India and retains a distinct Franco-Indian cultural heritage.
  • C. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • D. Nitibe
    Nitibe is an administrative post and rural area within the Oecusse exclave of Timor-Leste, known for its coastal and agricultural communities.
  • E. Madura
    Madura is an island off the northeastern coast of Java in Indonesia, known for its distinct Madurese culture and traditional bull races.
  • 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: Luyana
Triple: [Lozi, influencedBy, Luyana]
Generated description
Luyana is a Bantu language of southwestern Africa that historically served as a prestige and source language for the development of the Lozi language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Luyana
Target entity description: Luyana is a Bantu language of southwestern Africa that historically served as a prestige and source language for the development of the Lozi language.
  • A. Tianeti
    Tianeti is a small town and administrative center in eastern Georgia, situated in the mountainous Mtskheta-Mtianeti region.
  • B. Yanaon
    Yanaon is the former name of Yanam, a small coastal town in India that was once part of French India and retains a distinct Franco-Indian cultural heritage.
  • C. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • D. Nitibe
    Nitibe is an administrative post and rural area within the Oecusse exclave of Timor-Leste, known for its coastal and agricultural communities.
  • E. Madura
    Madura is an island off the northeastern coast of Java in Indonesia, known for its distinct Madurese culture and traditional bull races.
  • 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_69a88b05910c8190a9a2b1ff230c85f9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc1ea6cc88190982527774223127f completed March 7, 2026, 6:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f0ed1b881909ba3c7f9fea50267 completed March 9, 2026, 8:04 a.m.
NEDg Description generation batch_69ae7fee12ac8190bb9924f7467434a6 completed March 9, 2026, 8:08 a.m.
NED2 Entity disambiguation (via description) batch_69ae8061cd348190b0b0b65dcf730f99 completed March 9, 2026, 8:10 a.m.
Created at: March 4, 2026, 7:48 p.m.