Triple

T10807356
Position Surface form Disambiguated ID Type / Status
Subject Basu E255002 entity
Predicate hasLanguageForm P6281 FINISHED
Object বোষু
বোষু হলো বাংলা ভাষায় ব্যবহৃত “Basu” উপাধির একটি আঞ্চলিক বা ধ্বনিগত রূপ।
 E888025 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: বোষু | Statement: [Basu, hasLanguageForm, বোষু]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: বোষু
Context triple: [Basu, hasLanguageForm, বোষু]
  • A. Bosha
    Bosha is an alternative name for the Lom people, a Romani-related ethnic group primarily found in the Caucasus region.
  • B. Bishutan
    Bishutan is a character in the Persian epic Shahnameh, known as the loyal brother of the hero Esfandiyar.
  • C. Bawku
    Bawku is a town in northeastern Ghana known as a commercial hub near the country’s border with Burkina Faso.
  • D. Boso
    Boso is the fictional dialogue partner and student of Anselm of Canterbury in the theological treatise "Cur Deus Homo," representing the questioning layperson in discussions about the Incarnation and Atonement.
  • E. Bogoso
    Bogoso is a mining town in southwestern Ghana known for its significant gold deposits and related industrial activities.
  • 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: বোষু
Triple: [Basu, hasLanguageForm, বোষু]
Generated description
বোষু হলো বাংলা ভাষায় ব্যবহৃত “Basu” উপাধির একটি আঞ্চলিক বা ধ্বনিগত রূপ।
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: বোষু
Target entity description: বোষু হলো বাংলা ভাষায় ব্যবহৃত “Basu” উপাধির একটি আঞ্চলিক বা ধ্বনিগত রূপ।
  • A. Bosha
    Bosha is an alternative name for the Lom people, a Romani-related ethnic group primarily found in the Caucasus region.
  • B. Bishutan
    Bishutan is a character in the Persian epic Shahnameh, known as the loyal brother of the hero Esfandiyar.
  • C. Bawku
    Bawku is a town in northeastern Ghana known as a commercial hub near the country’s border with Burkina Faso.
  • D. Boso
    Boso is the fictional dialogue partner and student of Anselm of Canterbury in the theological treatise "Cur Deus Homo," representing the questioning layperson in discussions about the Incarnation and Atonement.
  • E. Bogoso
    Bogoso is a mining town in southwestern Ghana known for its significant gold deposits and related industrial activities.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733b506488190921e6a1f4168dd9e completed April 9, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69de8513fe0881909d6833c85aac03a8 completed April 14, 2026, 6:19 p.m.
NEDg Description generation batch_69de8e6f3fac8190bcd1675978d6d6d7 completed April 14, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69de8fa679cc81909cb51035e5403ce9 completed April 14, 2026, 7:04 p.m.
Created at: April 8, 2026, 9:18 p.m.