Triple

T4783017
Position Surface form Disambiguated ID Type / Status
Subject Yangchenma E106410 entity
Predicate counterpartOf P6587 FINISHED
Object Saraswati E19478 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: Saraswati | Statement: [Yangchenma, counterpartOf, Saraswati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saraswati
Context triple: [Yangchenma, counterpartOf, Saraswati]
  • A. Saraswati chosen
    Saraswati is the Hindu goddess of knowledge, wisdom, music, and the arts, revered as the divine embodiment of learning and creative inspiration.
  • B. Saraswati River
    The Saraswati River is a legendary and partially identified ancient river of the Indian subcontinent, revered in Hindu tradition and Vedic texts as a sacred and life-giving waterway.
  • C. Swati
    Swati is a Bantu language of the Nguni group, primarily spoken in Eswatini and parts of South Africa.
  • D. Sarayu
    Sarayu is a significant river in northern India, traditionally associated with the ancient city of Ayodhya and revered in Hindu mythology.
  • E. Ganga
    Ganga is a queen associated with the ancient Kuru dynasty in Indian epic tradition, often linked to the river goddess personified in the Mahabharata.
  • 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_69bd43f4a9588190bf73e20bc27c03cc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65ad3a188190872e47e3a3bf504b completed March 20, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfe31f64c88190b093e2bd65ae731b completed March 22, 2026, 12:39 p.m.
Created at: March 20, 2026, 1:22 p.m.