Triple

T23170833
Position Surface form Disambiguated ID Type / Status
Subject Harshacharita E578853 entity
Predicate mentions P831 FINISHED
Object Nalanda 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: Nalanda | Statement: [Harshacharita, mentions, Nalanda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nalanda
Context triple: [Harshacharita, mentions, Nalanda]
  • A. Nalanda chosen
    Nalanda is an ancient Buddhist monastic university and renowned archaeological site in present-day Bihar, India, celebrated as one of the world’s earliest centers of higher learning.
  • B. Nalanda Gedige
    Nalanda Gedige is an ancient, centrally located Sri Lankan temple ruin notable for its unique fusion of Hindu and Buddhist architectural and iconographic elements.
  • C. Vikramashila
    Vikramashila was a major medieval Buddhist monastic university in eastern India, renowned as a center of advanced Vajrayana and scholastic studies.
  • D. Nava Nalanda Mahavihara
    Nava Nalanda Mahavihara is a deemed university and research institution in Bihar, India, dedicated to the study and revival of ancient Nalanda’s Buddhist and Pali scholarship.
  • E. Odantapuri
    Odantapuri was an important early Buddhist monastic university in eastern India, renowned as a major center of learning and scholarship in the Pala period.
  • 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_69e245fd2a388190b814c0dfa15f7148 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f3007108190bc3c831f81ae1dce completed April 29, 2026, 4:55 a.m.
Created at: April 17, 2026, 4:03 p.m.