Triple

T6084917
Position Surface form Disambiguated ID Type / Status
Subject Usha Mangeshkar E135613 entity
Predicate givenName P17 FINISHED
Object Usha E448882 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: Usha | Statement: [Usha Mangeshkar, givenName, Usha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Usha
Context triple: [Usha Mangeshkar, givenName, Usha]
  • A. Usha chosen
    Usha is a goddess in Hindu mythology, often associated with the dawn and revered as a radiant divine figure.
  • B. Usha
    Usha was an ancient Galilean town that served as a major center of Jewish rabbinic leadership and legal activity during the period of the Sanhedrin in Roman-era Palestine.
  • C. Bharati
    Bharati is an epithet of the Hindu goddess Saraswati, highlighting her role as the divine embodiment of eloquence, learning, and the arts.
  • D. Shipra
    Shipra is a sacred river in the Indian state of Madhya Pradesh, especially revered in Ujjain as a major Hindu pilgrimage site.
  • E. Vinata
    Vinata is a figure in Hindu mythology known as the mother of Garuda and a consort of the sage Kashyapa.
  • 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_69c0087bcc788190b20f093d3a6c60ec completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057891dc88190997c4e32b2261fb3 completed March 22, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d5c743c81908a3454af2caa10a1 completed March 23, 2026, 11 a.m.
Created at: March 22, 2026, 4:12 p.m.