Triple

T4823561
Position Surface form Disambiguated ID Type / Status
Subject Karna E107766 entity
Predicate adoptiveFather P4385 FINISHED
Object Adhiratha
Adhiratha is a charioteer in the Mahabharata who finds and raises the abandoned infant Karna as his own son.
 E481784 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: Adhiratha | Statement: [Karna, adoptiveFather, Adhiratha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Adhiratha
Context triple: [Karna, adoptiveFather, Adhiratha]
  • A. Akrura
    Akrura is a revered figure in Hindu mythology, known as a devout Yadava charioteer and ally of Krishna who played a key role in bringing him to Mathura.
  • B. Saketa
    Saketa is the ancient name of the historic Indian city now known as Ayodhya, a major cultural and religious center in Hindu tradition.
  • C. Saartha
    Saartha is a renowned Kannada novel by S. L. Bhyrappa that explores philosophical, cultural, and spiritual themes through a journey set in ancient India.
  • D. Meghnad
    Meghnad is a given name most notably associated with Indian astrophysicist Meghnad Saha, renowned for his pioneering work on thermal ionization and stellar spectra.
  • E. Ashwapati
    Ashwapati is a king in the Hindu epic Ramayana, best known as the ruler of the kingdom of Kekaya and the father of Queen Kaikeyi.
  • 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: Adhiratha
Triple: [Karna, adoptiveFather, Adhiratha]
Generated description
Adhiratha is a charioteer in the Mahabharata who finds and raises the abandoned infant Karna as his own son.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Adhiratha
Target entity description: Adhiratha is a charioteer in the Mahabharata who finds and raises the abandoned infant Karna as his own son.
  • A. Akrura
    Akrura is a revered figure in Hindu mythology, known as a devout Yadava charioteer and ally of Krishna who played a key role in bringing him to Mathura.
  • B. Saketa
    Saketa is the ancient name of the historic Indian city now known as Ayodhya, a major cultural and religious center in Hindu tradition.
  • C. Saartha
    Saartha is a renowned Kannada novel by S. L. Bhyrappa that explores philosophical, cultural, and spiritual themes through a journey set in ancient India.
  • D. Meghnad
    Meghnad is a given name most notably associated with Indian astrophysicist Meghnad Saha, renowned for his pioneering work on thermal ionization and stellar spectra.
  • E. Ashwapati
    Ashwapati is a king in the Hindu epic Ramayana, best known as the ruler of the kingdom of Kekaya and the father of Queen Kaikeyi.
  • 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_69bd43f9efa081908314cb3e94fa1695 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6cac2bd08190b3f7cfe691fed052 completed March 20, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69be778a642081908761067765ba09c8 completed March 21, 2026, 10:48 a.m.
NEDg Description generation batch_69be7a75b1bc81909f575c82e58234f0 completed March 21, 2026, 11:01 a.m.
NED2 Entity disambiguation (via description) batch_69be7b020eec8190ad00fc36622fe6cd completed March 21, 2026, 11:03 a.m.
Created at: March 20, 2026, 1:24 p.m.