Triple

T12226982
Position Surface form Disambiguated ID Type / Status
Subject Maratha administration E291376 entity
Predicate usesTitle P10405 FINISHED
Object Kulkarni
Kulkarni is a traditional village-level official in the Maratha administrative system responsible for maintaining land and revenue records.
E972832 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: Kulkarni | Statement: [Maratha administration, usesTitle, Kulkarni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kulkarni
Context triple: [Maratha administration, usesTitle, Kulkarni]
  • A. Bhonsle
    The Bhonsle were a prominent Maratha royal dynasty best known for producing Chhatrapati Shivaji, founder of the Maratha Empire in western India.
  • B. Sankhali
    Sankhali is a village located in the North Goa district of the Indian state of Goa.
  • C. Parulkar
    Parulkar was a notable Indian social worker and nationalist associated with the Servants of India Society, an organization dedicated to public service and social reform.
  • D. Kathrada
    Kathrada is a South African surname most prominently associated with anti-apartheid activist and political prisoner Ahmed Kathrada.
  • E. Karanth
    Karanth is an Indian surname most prominently associated with the renowned writer and environmentalist Kota Shivarama Karanth.
  • 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: Kulkarni
Triple: [Maratha administration, usesTitle, Kulkarni]
Generated description
Kulkarni is a traditional village-level official in the Maratha administrative system responsible for maintaining land and revenue records.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kulkarni
Target entity description: Kulkarni is a traditional village-level official in the Maratha administrative system responsible for maintaining land and revenue records.
  • A. Bhonsle
    The Bhonsle were a prominent Maratha royal dynasty best known for producing Chhatrapati Shivaji, founder of the Maratha Empire in western India.
  • B. Sankhali
    Sankhali is a village located in the North Goa district of the Indian state of Goa.
  • C. Parulkar
    Parulkar was a notable Indian social worker and nationalist associated with the Servants of India Society, an organization dedicated to public service and social reform.
  • D. Kathrada
    Kathrada is a South African surname most prominently associated with anti-apartheid activist and political prisoner Ahmed Kathrada.
  • E. Karanth
    Karanth is an Indian surname most prominently associated with the renowned writer and environmentalist Kota Shivarama Karanth.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ca2101c8190955c36704935036a completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aa9023881909f8373e02d2cad4b completed May 2, 2026, 2:31 p.m.
NEDg Description generation batch_69f61a13fd1481908a06ca65b276e0e1 completed May 2, 2026, 3:36 p.m.
NED2 Entity disambiguation (via description) batch_69f61ad2bd0c8190ada37bc1f8ae160f completed May 2, 2026, 3:40 p.m.
Created at: April 8, 2026, 9:51 p.m.