Triple

T23050065
Position Surface form Disambiguated ID Type / Status
Subject Zaki Rostom E573984 entity
Predicate name P16 FINISHED
Object Zaki Rostom 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 Rostom | Statement: [Zaki Rostom, name, Zaki Rostom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zaki Rostom
Context triple: [Zaki Rostom, name, Zaki Rostom]
  • A. Zaki Rostom chosen
    Zaki Rostom was a prominent Egyptian actor known for his powerful portrayals of complex, often villainous characters in classic mid-20th-century Egyptian cinema.
  • B. Zaki Nour
    Zaki Nour was an Egyptian archaeologist known for unearthing the ancient solar barque of Pharaoh Khufu near the Great Pyramid at Giza.
  • C. Zaki Salam
    Zaki Salam is a notable individual recognized as a distinguished bearer of the surname Salam.
  • D. Ali Zeidan
    Ali Zeidan is a Libyan politician and former prime minister who led the country during its turbulent post-Gaddafi transition period.
  • E. Ali Rabeh
    Ali Rabeh is a French politician known for serving as the mayor of the suburban Parisian commune of Trappes.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867b800881909fabf9dca994c9e7 completed April 29, 2026, 4:18 a.m.
Created at: April 17, 2026, 3:54 p.m.