Triple

T56820
Position Surface form Disambiguated ID Type / Status
Subject India E1124 entity
Predicate recognizedLanguage P238 FINISHED
Object Marathi E3586 NE FINISHED

How this triple was built (2 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: Marathi | Statement: [India, recognizedLanguage, Marathi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marathi
Context triple: [India, recognizedLanguage, Marathi]
  • A. Marathi language chosen
    Marathi language is an Indo-Aryan language predominantly spoken in the Indian state of Maharashtra and surrounding regions, with a rich literary tradition and official status in the state.
  • B. Hindi
    Hindi is an Indo-Aryan language widely spoken across northern and central India and used in government, education, media, and popular culture.
  • C. Sanskrit
    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.
  • D. Telugu
    Telugu is a major Dravidian language predominantly spoken in the Indian states of Andhra Pradesh and Telangana, known for its rich literary tradition and classical status.
  • E. Bengali
    Bengali is an Indo-Aryan language spoken primarily in the Bengal region of South Asia and serving as the official and most widely used language of Bangladesh and the Indian state of West Bengal.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a248adc5b48190aa8db9fb092fb28a completed Feb. 28, 2026, 1:45 a.m.
NER Named-entity recognition batch_69a24b07f4a881909e32115e84da02a3 completed Feb. 28, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69a25ab7ec3881909356c659f4664fb8 completed Feb. 28, 2026, 3:02 a.m.
Created at: Feb. 28, 2026, 1:50 a.m.