Triple

T124872
Position Surface form Disambiguated ID Type / Status
Subject Kawi (Old Javanese) E2524 entity
Predicate lexicalBorrowingFrom P1754 FINISHED
Object Sanskrit E3683 NE FINISHED

How this triple was built (3 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: Sanskrit | Statement: [Kawi (Old Javanese), lexicalBorrowingFrom, Sanskrit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanskrit
Context triple: [Kawi (Old Javanese), lexicalBorrowingFrom, Sanskrit]
  • A. Sanskrit chosen
    Sanskrit is an ancient Indo-Aryan language of India, foundational to Hindu religious texts and classical Indian literature, and a key source for many modern South Asian languages.
  • B. Maithili
    Maithili is an Indo-Aryan language spoken primarily in the eastern Indian state of Bihar and neighboring regions, with a rich literary tradition and official recognition in India.
  • C. Hindi
    Hindi is an Indo-Aryan language widely spoken across northern and central India and used in government, education, media, and popular culture.
  • D. Devanagari script
    Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
  • E. Indo-Aryan languages
    Indo-Aryan languages are a major branch of the Indo-European family spoken primarily in the Indian subcontinent, including languages such as Hindi, Bengali, Punjabi, and Marathi.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: lexicalBorrowingFrom
Context triple: [Kawi (Old Javanese), lexicalBorrowingFrom, Sanskrit]
  • A. hasCommonLoanwordsFrom
    Indicates that two languages share loanwords that originate from the same source language.
  • B. influencedLanguage
    Indicates that one language has had an effect on the development, structure, or usage of another language.
  • C. etymologicalLanguage
    Indicates the language from which a word or term is historically derived in its etymology.
  • D. hasLanguageOfOrigin chosen
    Indicates that one entity has its origin or source in the language specified by another entity.
  • E. hasCognate
    Indicates that two linguistic forms in different languages share a common historical origin, typically descending from the same ancestral word.
  • F. None of above.

Provenance (4 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_69a251b54ea88190b18281669f59b4c0 completed Feb. 28, 2026, 2:23 a.m.
NER Named-entity recognition batch_69a2573e4e6481908252dfef2e34f46e completed Feb. 28, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69a29e494ef08190b8c5b5f8d52251c8 completed Feb. 28, 2026, 7:50 a.m.
PD Predicate disambiguation batch_69a2564a54948190ba30bee858173b27 completed Feb. 28, 2026, 2:43 a.m.
Created at: Feb. 28, 2026, 2:27 a.m.