Triple

T21330855
Position Surface form Disambiguated ID Type / Status
Subject Mohan Agashe E525893 entity
Predicate notableWork P4 FINISHED
Object Samna 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: Samna | Statement: [Mohan Agashe, notableWork, Samna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samna
Context triple: [Mohan Agashe, notableWork, Samna]
  • A. Samna chosen
    Samna is a critically acclaimed Marathi political drama film directed by Jabbar Patel, known for its bold exploration of corruption and power dynamics in rural India.
  • B. Saman
    Saman is a revered Sinhalese deity and guardian god of Sri Lanka, particularly venerated as the protector of the sacred mountain Adam’s Peak.
  • C. Saman
    Saman is a small city in central Iran known for its scenic riverside landscapes and agricultural orchards.
  • D. Symra
    Symra is a collection of poems by Norwegian linguist and poet Ivar Aasen, reflecting his pioneering use and development of the Nynorsk written language.
  • E. Sandane
    Sandane is a village in Vestland county, Norway, known as the main settlement and hub of the Gloppen municipality.
  • 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7ab5177dc8190b888351e9a45b45f completed April 21, 2026, 4:52 p.m.
Created at: April 16, 2026, 4:42 p.m.