Triple

T6240315
Position Surface form Disambiguated ID Type / Status
Subject Chanakya E139582 entity
Predicate notableWork P4 FINISHED
Object Arthashastra E102080 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: Arthashastra | Statement: [Chanakya, notableWork, Arthashastra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arthashastra
Context triple: [Chanakya, notableWork, Arthashastra]
  • A. Arthashastra chosen
    Arthashastra is an ancient Indian treatise on statecraft, economics, and military strategy, traditionally attributed to Kautilya (Chanakya), that outlines detailed principles of governance and political power.
  • B. Culikasutras
    Culikasutras are a set of Jain Āgama scriptures that form part of the canonical religious literature of Jainism.
  • C. Mulasutras
    Mulasutras are foundational Jain canonical texts that outline core doctrines, ethical principles, and monastic disciplines within the Agama literature.
  • D. Nyaya Sutras
    The Nyaya Sutras are an ancient Indian philosophical text that systematizes logic, epistemology, and debate within the Nyaya school of Hindu philosophy.
  • E. Hitopadesha
    Hitopadesha is a classic Sanskrit collection of animal fables and moral tales, traditionally used to teach ethics and practical wisdom.
  • 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_69c008b1c5088190ae6de2555fc05ad8 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063067d9c819085a18d9d03939266 completed March 22, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20e07bff8819091ca881c9b4daaf6 completed March 24, 2026, 4:07 a.m.
Created at: March 22, 2026, 4:23 p.m.