Triple

T4959826
Position Surface form Disambiguated ID Type / Status
Subject Drona Parva E111376 entity
Predicate mainLocation P3231 FINISHED
Object Kurukshetra E18593 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: Kurukshetra | Statement: [Drona Parva, mainLocation, Kurukshetra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurukshetra
Context triple: [Drona Parva, mainLocation, Kurukshetra]
  • A. Kurukshetra battlefield chosen
    Kurukshetra battlefield is the legendary war site in the Indian epic Mahabharata where the dialogue between Prince Arjuna and Lord Krishna, recorded as the Bhagavad Gita, takes place.
  • B. Hastinapura
    Hastinapura is the ancient royal capital of the Kuru kingdom in Indian epic tradition, serving as the primary political and familial setting of the Mahabharata.
  • C. Ayodhya
    Ayodhya is an ancient city in India revered in Hinduism as the birthplace of Lord Rama and a major pilgrimage site.
  • D. Thanesar
    Thanesar is a historic town in the Indian state of Haryana, renowned as an ancient center of learning and a significant site in Hindu mythology and the Mahabharata.
  • E. Kannauj
    Kannauj is a historic town and parliamentary constituency in Uttar Pradesh, India, renowned for its ancient heritage and traditional perfume (attar) industry.
  • 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_69bd4418390c8190b7e9766a2512ce55 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71da80008190a0d606d5091822b8 completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea46c12c481909aed42f9b45cde81 completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:32 p.m.