Triple

T21089066
Position Surface form Disambiguated ID Type / Status
Subject Zaki Azmi E519583 entity
Predicate name P16 FINISHED
Object Zaki Azmi 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: Zaki Azmi | Statement: [Zaki Azmi, name, Zaki Azmi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zaki Azmi
Context triple: [Zaki Azmi, name, Zaki Azmi]
  • A. Zaki Azmi chosen
    Zaki Azmi is a prominent Malaysian jurist and former Chief Justice of Malaysia who later served as Chief Justice of the DIFC Courts in Dubai.
  • B. Kaifi Azmi
    Kaifi Azmi was a renowned Indian Urdu poet, lyricist, and social activist known for his progressive, socially conscious writing and influential contributions to Indian literature and cinema.
  • C. Irshad Kamil
    Irshad Kamil is a prominent Indian lyricist best known for his poetic and emotionally resonant songs in contemporary Hindi cinema.
  • D. Najeeb Khan
    Najeeb Khan is an Indian cinematographer best known for his work on the iconic 1992 coming-of-age sports film "Jo Jeeta Wohi Sikandar."
  • E. Salim Akil
    Salim Akil is an American television and film director, writer, and producer best known for his work on projects like the TV series "Girlfriends," "The Game," and "Black Lightning."
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094dd65481909391ed74115afc23 completed April 21, 2026, 5:21 a.m.
Created at: April 16, 2026, 2:50 p.m.