Triple

T21428654
Position Surface form Disambiguated ID Type / Status
Subject Akshay Kumar E528625 entity
Predicate notableWork P4 FINISHED
Object Special 26 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: Special 26 | Statement: [Akshay Kumar, notableWork, Special 26]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Special 26
Context triple: [Akshay Kumar, notableWork, Special 26]
  • A. Special 26 chosen
    Special 26 is a 2013 Indian heist thriller film inspired by real-life 1980s cons, known for its ensemble cast and clever plot about conmen posing as government officials.
  • B. Udta Punjab
    Udta Punjab is a 2016 Indian crime drama film that explores the drug abuse crisis in the state of Punjab through the intersecting lives of several characters.
  • C. Tehelka
    Tehelka is an Indian news magazine and investigative journalism outlet known for its hard-hitting exposés on political and corporate corruption.
  • D. Sarkar
    Sarkar is a 2018 Tamil-language political action film directed by A.R. Murugadoss and starring Vijay, known for its themes of electoral reform and its commercial success in Indian cinema.
  • E. Sarkar
    Sarkar was a key revenue and administrative unit in the Maratha Empire, functioning as a mid-level territorial division for governance and tax collection.
  • 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_69e0c455f3688190810bc96365791b0f completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee813db52c8190ac933bc6ec4dbf77 completed April 26, 2026, 9:18 p.m.
Created at: April 16, 2026, 5:49 p.m.