Triple

T22667333
Position Surface form Disambiguated ID Type / Status
Subject Lakshmi E559825 entity
Predicate epithet P743 FINISHED
Object Padma NE NERFINISHED

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: Padma | Statement: [Lakshmi, epithet, Padma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Padma
Context triple: [Lakshmi, epithet, Padma]
  • A. Padma
    Padma is a practical, earthy woman in Salman Rushdie’s novel "Midnight’s Children" who serves as Saleem Sinai’s lover and skeptical yet grounding listener to his fantastical life story.
  • B. Padma chosen
    Padma is a Hindu goddess associated with prosperity and purity, often identified with Lakshmi and revered as the divine consort of the celestial physician Dhanvantari.
  • C. Vaijayanti
    Vaijayanti is the ancient name of Banavasi, a historic town in Karnataka, India, renowned as one of the oldest centers of Hindu and Jain culture in the region.
  • D. Vasundhara
    Vasundhara is a revered Hindu earth goddess, often identified with Bhudevi as the personification of the fertile, life-sustaining Earth.
  • E. Nagadeepa
    Nagadeepa is a small but historically and religiously significant island off the northern coast of Sri Lanka, revered by both Buddhists and Hindus for its ancient temples and pilgrimage sites.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1781ceca08190ba1309570e81c5af completed April 29, 2026, 3:16 a.m.
Created at: April 17, 2026, 3:09 p.m.