Triple

T6420001
Position Surface form Disambiguated ID Type / Status
Subject Santhal E127920 entity
Predicate notableFestival P26210 FINISHED
Object Karam E377787 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: Karam | Statement: [Santhal, notableFestival, Karam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karam
Context triple: [Santhal, notableFestival, Karam]
  • A. Karam chosen
    Karam is a given name commonly used in South Asian and Middle Eastern cultures, often associated with meanings of generosity and nobility.
  • B. Khar
    Khar is a suburban neighborhood in Mumbai, India, known for its residential areas, shopping streets, and proximity to the Arabian Sea.
  • C. Karao
    Karao is an Austronesian language spoken by a small indigenous community in the Philippines.
  • D. Kifri
    Kifri is a town in Iraq with a significant Iraqi Turkmen population and cultural presence.
  • E. Karaikal
    Karaikal is a coastal town and district of the Union Territory of Puducherry in southeastern India, known for its strategic port and location along the Bay of Bengal.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c06902ddb48190bd5a8b5ecdf6c39e completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640d5f6f88190963a1e59400c7aa0 completed March 27, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:43 p.m.