Triple

T14066681
Position Surface form Disambiguated ID Type / Status
Subject Taharqa E338492 entity
Predicate relative P37 FINISHED
Object Shabaka E157667 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: Shabaka | Statement: [Taharqa, relative, Shabaka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shabaka
Context triple: [Taharqa, relative, Shabaka]
  • A. Shabaka chosen
    Shabaka was a Kushite pharaoh of Egypt’s 25th Dynasty, known for reviving traditional Egyptian culture and religion during his reign in the 8th century BCE.
  • B. Naglaa
    Naglaa is an Arabic feminine given name commonly used in Egypt and other Arabic-speaking countries.
  • C. Raneb
    Raneb was an early ancient Egyptian pharaoh of the Second Dynasty, known for his association with the sun god Ra and for helping consolidate royal power in the formative period of the Egyptian state.
  • D. Gamila
    Gamila is the highest peak of Mount Tymfi in the Pindus mountain range of northwestern Greece.
  • E. Bab Guissa
    Bab Guissa is a historic northern gate of the old city of Fez in Morocco, serving as one of the main entrances to its medieval medina.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de568b81f08190a571004261c0e8e4 completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb669111081909ccd167f41571a00 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:21 p.m.