Triple

T12226999
Position Surface form Disambiguated ID Type / Status
Subject Maratha administration E291376 entity
Predicate leviesTax P25448 FINISHED
Object sardeshmukhi E58488 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: sardeshmukhi | Statement: [Maratha administration, leviesTax, sardeshmukhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sardeshmukhi
Context triple: [Maratha administration, leviesTax, sardeshmukhi]
  • A. Sardeshmukhi chosen
    Sardeshmukhi was a tax levied by the Maratha Empire, typically an additional surcharge claimed by Maratha rulers over and above regular land revenue in territories under their influence.
  • B. Sorkhpooshan
    Sorkhpooshan is a popular nickname for Persepolis F.C., one of Iran’s most successful and widely supported football clubs.
  • C. Sirkhi
    Sirkhi is a dialect of the Dargin language, spoken by a subgroup of the Dargin people in the North Caucasus region of Russia.
  • D. Akaler Sandhane
    Akaler Sandhane is a critically acclaimed 1980 Bengali film by director Mrinal Sen that explores the lingering social and psychological impact of the 1943 Bengal famine through a film-within-a-film narrative.
  • E. Sawerigadi
    Sawerigadi is a town in Indonesia located in the province of Southeast Sulawesi.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93ed7251c8190b94d7cd75ad49b9c completed April 10, 2026, 6:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aa9023881909f8373e02d2cad4b completed May 2, 2026, 2:31 p.m.
Created at: April 8, 2026, 9:51 p.m.