Triple

T1410208
Position Surface form Disambiguated ID Type / Status
Subject Kartikeya E31785 entity
Predicate consort P13 FINISHED
Object Devasena
Devasena is a Hindu goddess known as one of the wives of the war god Kartikeya, often associated with valor and divine grace.
 E161608 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: Devasena | Statement: [Kartikeya, consort, Devasena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Devasena
Context triple: [Kartikeya, consort, Devasena]
  • A. Chitrangada
    Chitrangada is a warrior princess from the Indian epic Mahabharata, known as one of Arjuna’s wives and the daughter of the king of Manipur.
  • B. Devi
    Devi is the supreme goddess in Hinduism, embodying the divine feminine power (Shakti) in its many forms such as Durga, Parvati, Lakshmi, and Saraswati.
  • C. Rukmini
    Rukmini is a principal queen of the Hindu god Krishna, revered as an incarnation of the goddess Lakshmi and celebrated for her devotion and role in Krishna’s life.
  • D. Madhura
    Madhura is an ancient name for the historic North Indian city of Mathura, a major cultural and religious center associated with Hindu traditions.
  • E. Pranhita
    Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
  • 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: Devasena
Triple: [Kartikeya, consort, Devasena]
Generated description
Devasena is a Hindu goddess known as one of the wives of the war god Kartikeya, often associated with valor and divine grace.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Devasena
Target entity description: Devasena is a Hindu goddess known as one of the wives of the war god Kartikeya, often associated with valor and divine grace.
  • A. Chitrangada
    Chitrangada is a warrior princess from the Indian epic Mahabharata, known as one of Arjuna’s wives and the daughter of the king of Manipur.
  • B. Devi
    Devi is the supreme goddess in Hinduism, embodying the divine feminine power (Shakti) in its many forms such as Durga, Parvati, Lakshmi, and Saraswati.
  • C. Rukmini
    Rukmini is a principal queen of the Hindu god Krishna, revered as an incarnation of the goddess Lakshmi and celebrated for her devotion and role in Krishna’s life.
  • D. Madhura
    Madhura is an ancient name for the historic North Indian city of Mathura, a major cultural and religious center associated with Hindu traditions.
  • E. Pranhita
    Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
  • 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_69ace57be14881908d469d2b5333d6d5 completed March 8, 2026, 2:57 a.m.
NEDg Description generation batch_69ace61c6f348190bba7717b1bd7f24a completed March 8, 2026, 2:59 a.m.
NED2 Entity disambiguation (via description) batch_69ace6eeb99081908ac23a6c71faeae6 completed March 8, 2026, 3:03 a.m.
Created at: March 1, 2026, 7:59 p.m.