Triple

T21943871
Position Surface form Disambiguated ID Type / Status
Subject Irrfan Khan E541887 entity
Predicate givenName P17 FINISHED
Object Irfan 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: Irfan | Statement: [Irrfan Khan, givenName, Irfan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irfan
Context triple: [Irrfan Khan, givenName, Irfan]
  • A. Irfan chosen
    Irfan is the given name of the acclaimed Indian actor Irrfan Khan, known for his work in both Bollywood and international cinema.
  • B. Rohilla Pathan
    Rohilla Pathan refers to members of a Pashtun (Pathan) warrior community historically settled in northern India, particularly known for their role in the Rohilkhand region during the 18th century.
  • C. Sikandar Raza
    Sikandar Raza is a Zimbabwean international cricketer known as a key all-rounder and match-winner in limited-overs formats.
  • D. Mohammad Irfan
    Mohammad Irfan is a Pakistani left-arm fast bowler known for his exceptional height and ability to generate steep bounce, who has played international cricket across formats and in various T20 leagues.
  • E. Sarfaraz Khan
    Sarfaraz Khan was an 18th-century Nawab of Bengal, Bihar, and Orissa in the Mughal era, known for his brief and turbulent rule that ended with his defeat by Alivardi Khan.
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1242515ec8190b015bf8c7b13be85 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.