Triple

T2894875
Position Surface form Disambiguated ID Type / Status
Subject Majha E63912 entity
Predicate hasFestival P3113 FINISHED
Object Vaisakhi E63433 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: Vaisakhi | Statement: [Majha, hasFestival, Vaisakhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vaisakhi
Context triple: [Majha, hasFestival, Vaisakhi]
  • A. Vaisakhi chosen
    Vaisakhi is a major spring harvest festival and Sikh religious celebration marking the formation of the Khalsa and the Punjabi New Year.
  • B. Gudi Padwa
    Gudi Padwa is a major spring festival marking the Marathi New Year, celebrated with rituals, colorful decorations, and the raising of a symbolic gudi flag.
  • C. Vishu
    Vishu is a major spring festival in Kerala that marks the traditional New Year in the Malayalam calendar, celebrated with rituals like Vishukkani, fireworks, and festive feasts.
  • D. Lohri
    Lohri is a popular Punjabi winter harvest festival celebrated with bonfires, folk songs, and traditional foods to mark the end of the winter solstice.
  • E. Dussehra
    Dussehra is a major Hindu festival that celebrates the victory of good over evil, most prominently marked in northern India by the burning of effigies of the demon king Ravana.
  • 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_69ab4c45822c8190830c5f2bb97bcfd0 completed March 6, 2026, 9:51 p.m.
NER Named-entity recognition batch_69abe06509808190b673222b9ae3d599 completed March 7, 2026, 8:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69b108cc4870819081e68032517468a8 completed March 11, 2026, 6:16 a.m.
Created at: March 6, 2026, 10:07 p.m.