Triple

T9640615
Position Surface form Disambiguated ID Type / Status
Subject Mycerinus E233054 entity
Predicate predecessor P97 FINISHED
Object Khafre E33000 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: Khafre | Statement: [Mycerinus, predecessor, Khafre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khafre
Context triple: [Mycerinus, predecessor, Khafre]
  • A. Khafre chosen
    Khafre was an ancient Egyptian pharaoh of the Fourth Dynasty, best known for commissioning the second-largest pyramid at Giza and likely the Great Sphinx.
  • B. Khufu
    Khufu was an ancient Egyptian pharaoh of the Fourth Dynasty, best known for commissioning the construction of the Great Pyramid at Giza.
  • C. Mycerinus
    Mycerinus is the Greek name for Menkaure, the ancient Egyptian pharaoh best known for building the third and smallest of the three main pyramids at Giza.
  • D. Radjedef
    Radjedef was an ancient Egyptian pharaoh of the 4th Dynasty, likely a son of Khufu, who ruled from Giza and is known for building a pyramid at Abu Rawash.
  • E. Kahmunrah
    Kahmunrah is the power-hungry ancient Egyptian pharaoh and main antagonist in the film "Night at the Museum: Battle of the Smithsonian."
  • 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_69ca848a5a908190aad251f4137b0c3a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b552a1c81909a1fab347110eeb1 completed April 1, 2026, 10:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1af6abb008190860e4742656baa97 completed April 5, 2026, 12:40 a.m.
Created at: March 30, 2026, 8:12 p.m.