Triple

T22903173
Position Surface form Disambiguated ID Type / Status
Subject Faculty of Arts, Banaras Hindu University E568376 entity
Predicate hasDepartment P35 FINISHED
Object Department of Urdu 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: Department of Urdu | Statement: [Faculty of Arts, Banaras Hindu University, hasDepartment, Department of Urdu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Department of Urdu
Context triple: [Faculty of Arts, Banaras Hindu University, hasDepartment, Department of Urdu]
  • A. Department of Urdu chosen
    The Department of Urdu is an academic unit dedicated to teaching and research in the Urdu language and its literature.
  • B. Department of Punjabi
    The Department of Punjabi is an academic unit dedicated to the study, research, and promotion of the Punjabi language, literature, and culture.
  • C. Department of Hindi
    The Department of Hindi at Jesus and Mary College, University of Delhi, is an academic unit dedicated to teaching and research in Hindi language and literature.
  • D. Department of Hindi
    The Department of Hindi is an academic unit at Kashi Vidyapith dedicated to teaching and research in Hindi language and literature.
  • E. Department of Hindi
    The Department of Hindi is an academic unit at Punjabi University, Patiala, dedicated to teaching and research in Hindi language and literature.
  • 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_69e2458cd9e48190943ad2e34485d939 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18017a0208190a7e6f1638fc17b01 completed April 29, 2026, 3:50 a.m.
Created at: April 17, 2026, 3:41 p.m.