Triple

T12789082
Position Surface form Disambiguated ID Type / Status
Subject Berar E305708 entity
Predicate historicalName P65 FINISHED
Object Varhad E24233 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: Varhad | Statement: [Berar, historicalName, Varhad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Varhad
Context triple: [Berar, historicalName, Varhad]
  • A. Varhadi chosen
    Varhadi is a regional dialect of Marathi spoken primarily in the Vidarbha region of Maharashtra, India, known for its distinct phonetic and lexical features.
  • B. Savindan
    Savindan is the Serbian Orthodox holiday and cultural celebration honoring Saint Sava, the first Archbishop of the Serbian Church and patron of education.
  • C. Veeragase
    Veeragase is a vigorous and ritualistic folk dance-drama of Karnataka, India, traditionally performed during festivals to depict stories of valor from Hindu mythology.
  • D. Varaha
    Varaha is the boar incarnation of the Hindu god Vishnu, revered for rescuing the earth from cosmic waters and defeating the demon Hiranyaksha.
  • E. Varali
    Varali is a major and ancient Carnatic raga known for its distinctive, austere melodic character and frequent use in profound devotional compositions.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e6a61f48190972e241e70bc392c completed April 10, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68508e4488190bb57a1ade93987ab completed May 2, 2026, 11:13 p.m.
Created at: April 9, 2026, 5:30 p.m.