Triple

T6302684
Position Surface form Disambiguated ID Type / Status
Subject Jahangirnagar University E141292 entity
Predicate hasNotableAlumni P51 FINISHED
Object Humayun Azad E180194 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: Humayun Azad | Statement: [Jahangirnagar University, hasNotableAlumni, Humayun Azad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Humayun Azad
Context triple: [Jahangirnagar University, hasNotableAlumni, Humayun Azad]
  • A. Humayun Azad chosen
    Humayun Azad was a prominent Bangladeshi writer, linguist, and intellectual known for his influential and often controversial contributions to modern Bengali literature and secular thought.
  • B. Azad Rao Khan
    Azad Rao Khan is the son of prominent Indian actor and filmmaker Aamir Khan and his former wife Kiran Rao.
  • C. Sikandar Kher
    Sikandar Kher is an Indian film and television actor known for his work in Hindi cinema and web series.
  • D. Farrukh Dhondy
    Farrukh Dhondy is a British-Indian writer, playwright, and former commissioning editor for Channel 4 known for his works on race, politics, and South Asian history.
  • E. Ibrahim Ismail Chundrigar
    Ibrahim Ismail Chundrigar was a Pakistani politician and brief-serving Prime Minister known for his role in the early political leadership of Pakistan.
  • 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_69c008cf0ad4819095def81e2bd42f9f completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0645cfca88190ace060ef5b0e00e8 completed March 22, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d2cd75c81908961633a7ccf5dc9 completed March 27, 2026, 7:09 a.m.
Created at: March 22, 2026, 4:27 p.m.