Triple

T1410184
Position Surface form Disambiguated ID Type / Status
Subject Kartikeya E31785 entity
Predicate otherName P39 FINISHED
Object Subramanya
Subramanya is a Hindu deity of war and wisdom, widely revered in South India and identified with the god Kartikeya (Murugan).
E164754 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: Subramanya | Statement: [Kartikeya, otherName, Subramanya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Subramanya
Context triple: [Kartikeya, otherName, Subramanya]
  • A. Naraina
    Naraina is a locality in West Delhi, India, known for its mix of residential areas and industrial estates and its location along major city transport routes.
  • B. Narayana
    Narayana is a revered name of the Hindu god Vishnu, especially associated with his role as the supreme preserver and sustainer of the universe.
  • C. Venkata
    Venkata is the given name of Indian physicist and Nobel laureate C. V. Raman, renowned for discovering the Raman effect in light scattering.
  • D. Bhavani
    Bhavani is a significant river in southern India, known for flowing through Tamil Nadu and contributing majorly to the Kaveri river system.
  • E. Bhavani
    Bhavani is a fierce and protective form of the Hindu goddess Devi, often associated with power, motherhood, and the destruction of evil.
  • 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: Subramanya
Triple: [Kartikeya, otherName, Subramanya]
Generated description
Subramanya is a Hindu deity of war and wisdom, widely revered in South India and identified with the god Kartikeya (Murugan).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Subramanya
Target entity description: Subramanya is a Hindu deity of war and wisdom, widely revered in South India and identified with the god Kartikeya (Murugan).
  • A. Naraina
    Naraina is a locality in West Delhi, India, known for its mix of residential areas and industrial estates and its location along major city transport routes.
  • B. Narayana
    Narayana is a revered name of the Hindu god Vishnu, especially associated with his role as the supreme preserver and sustainer of the universe.
  • C. Venkata
    Venkata is the given name of Indian physicist and Nobel laureate C. V. Raman, renowned for discovering the Raman effect in light scattering.
  • D. Bhavani
    Bhavani is a significant river in southern India, known for flowing through Tamil Nadu and contributing majorly to the Kaveri river system.
  • E. Bhavani
    Bhavani is a fierce and protective form of the Hindu goddess Devi, often associated with power, motherhood, and the destruction of evil.
  • 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_69a49918e1f88190ba610f9dc8114578 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c3e0bfd08190a50820bc7585c28f completed March 1, 2026, 10:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08ae530081909695bde0d9c46d41 completed March 8, 2026, 5:27 a.m.
NEDg Description generation batch_69ad0975b0c4819095a36f833e15fdae completed March 8, 2026, 5:30 a.m.
NED2 Entity disambiguation (via description) batch_69ad0a1df32c81908bf57911901f3f9c completed March 8, 2026, 5:33 a.m.
Created at: March 1, 2026, 7:59 p.m.