Triple

T19596672
Position Surface form Disambiguated ID Type / Status
Subject Saraswati E470365 entity
Predicate otherName P39 FINISHED
Object Vagdevi
Vagdevi is a revered Hindu goddess associated with speech, wisdom, and learning, commonly identified with the goddess Saraswati.
 E1391995 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: Vagdevi | Statement: [Saraswati, otherName, Vagdevi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vagdevi
Context triple: [Saraswati, otherName, Vagdevi]
  • A. Gajalakshmi
    Gajalakshmi is a revered Hindu goddess form of Lakshmi depicted with elephants flanking her, symbolizing prosperity, abundance, and royal authority.
  • B. Sachi Devi
    Sachi Devi is revered in Gaudiya Vaishnavism as the pious and devoted mother of the saint and religious reformer Chaitanya Mahaprabhu.
  • C. Sachi Devi
    Sachi Devi was the wife of Jagannath Mishra, a noted Indian politician and former Chief Minister of Bihar.
  • D. Lalitha Devi
    Lalitha Devi is the royal figure after whom the historic Lalitha Mahal Palace in Mysore, India, was named.
  • E. Bhanumati
    Bhanumati is a character in the Indian epic Mahabharata, known as the queen of Hastinapura and wife of the Kaurava prince Duryodhana.
  • 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: Vagdevi
Triple: [Saraswati, otherName, Vagdevi]
Generated description
Vagdevi is a revered Hindu goddess associated with speech, wisdom, and learning, commonly identified with the goddess Saraswati.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vagdevi
Target entity description: Vagdevi is a revered Hindu goddess associated with speech, wisdom, and learning, commonly identified with the goddess Saraswati.
  • A. Gajalakshmi
    Gajalakshmi is a revered Hindu goddess form of Lakshmi depicted with elephants flanking her, symbolizing prosperity, abundance, and royal authority.
  • B. Sachi Devi
    Sachi Devi is revered in Gaudiya Vaishnavism as the pious and devoted mother of the saint and religious reformer Chaitanya Mahaprabhu.
  • C. Sachi Devi
    Sachi Devi was the wife of Jagannath Mishra, a noted Indian politician and former Chief Minister of Bihar.
  • D. Lalitha Devi
    Lalitha Devi is the royal figure after whom the historic Lalitha Mahal Palace in Mysore, India, was named.
  • E. Bhanumati
    Bhanumati is a character in the Indian epic Mahabharata, known as the queen of Hastinapura and wife of the Kaurava prince Duryodhana.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e6407b997881909762c8f919c9cdad completed April 20, 2026, 3:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ab8276e08190880ced76dbc7c938 completed May 15, 2026, 11:25 p.m.
NEDg Description generation batch_6a07af92c8808190a3787283c0648af7 completed May 15, 2026, 11:43 p.m.
NED2 Entity disambiguation (via description) batch_6a07b00e38408190a5a996d633630704 completed May 15, 2026, 11:45 p.m.
Created at: April 10, 2026, 1:43 p.m.