Triple

T20353069
Position Surface form Disambiguated ID Type / Status
Subject Vishvakarma E496066 entity
Predicate designed P184 FINISHED
Object Amaravati 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: Amaravati | Statement: [Vishvakarma, designed, Amaravati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amaravati
Context triple: [Vishvakarma, designed, Amaravati]
  • A. Amaravati chosen
    Amaravati is the opulent celestial capital city of the god Indra in Hindu mythology, famed as the heavenly abode of the Devas.
  • B. Amaravati
    Amaravati is an ancient Buddhist center in Andhra Pradesh, India, renowned for its historic stupa and archaeological significance.
  • C. Amaravati
    Amaravati is a planned riverfront city in southeastern India that serves as the capital of the state of Andhra Pradesh.
  • D. Vijayawada
    Vijayawada is a major commercial and cultural city in the Indian state of Andhra Pradesh, known as a key transportation hub and an important center for trade, education, and politics in the region.
  • E. Ravulapalem
    Ravulapalem is a town in the Indian state of Andhra Pradesh, known for its agricultural markets and location along key transport routes in the Godavari region.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67851c7088190ba960a33c6dfa824 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:25 a.m.