Triple

T279322
Position Surface form Disambiguated ID Type / Status
Subject Sevagram Ashram E5318 entity
Predicate locatedIn P40 FINISHED
Object Maharashtra E19223 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: Maharashtra | Statement: [Sevagram Ashram, locatedIn, Maharashtra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maharashtra
Context triple: [Sevagram Ashram, locatedIn, Maharashtra]
  • A. Maharashtra chosen
    Maharashtra is a large and economically significant state in western India, known for its capital Mumbai, the country’s financial hub, and its rich cultural and historical heritage.
  • B. Gujarat
    Gujarat is a western coastal state of India known for its significant role in trade and industry, rich cultural heritage, and historic cities such as Ahmedabad.
  • C. Uttar Pradesh
    Uttar Pradesh is a populous northern Indian state known for its political influence, rich cultural and religious heritage, and historic cities such as Varanasi and Agra.
  • D. Madhya Pradesh
    Madhya Pradesh is a large central Indian state known for its historical cities, diverse tribal cultures, and significant forested and wildlife areas including several major national parks.
  • E. Karnataka
    Karnataka is a state in southwestern India known for its diverse languages and cultures, major tech hub Bengaluru, and rich historical and architectural heritage.
  • 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_69a257e6c8788190987dfe705ca2912a completed Feb. 28, 2026, 2:50 a.m.
NER Named-entity recognition batch_69a25def95c48190bb8ab2259f67b583 completed Feb. 28, 2026, 3:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69a467f8341081909e4fbdbe44a2e799 completed March 1, 2026, 4:23 p.m.
Created at: Feb. 28, 2026, 2:59 a.m.