Triple

T801444
Position Surface form Disambiguated ID Type / Status
Subject Upper Egypt E17135 entity
Predicate historicalCapital P2536 FINISHED
Object Waset E98742 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: Waset | Statement: [Upper Egypt, historicalCapital, Waset]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Waset
Context triple: [Upper Egypt, historicalCapital, Waset]
  • A. Waset chosen
    Waset was the ancient Egyptian city known in Greek as Thebes, a major religious and political center along the Nile.
  • B. Dendera
    Dendera is an ancient Egyptian town best known for the well-preserved Temple of Hathor and its rich archaeological remains along the Nile.
  • C. Dender
    The Dender is a river in Belgium that flows through Wallonia and Flanders before joining the Scheldt near the city of Dendermonde.
  • D. Deshret
    Deshret is the ancient Egyptian Red Crown symbolizing the pharaonic authority and land of Lower Egypt.
  • E. Giza
    Giza is an Egyptian city on the west bank of the Nile, famous for the Giza Plateau where the Great Pyramids and the Sphinx are located.
  • 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_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cc75e88190bd35aabe51051b51 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3b1a81481908c831d1f43b9d014 completed March 4, 2026, 3:14 a.m.
Created at: March 1, 2026, 7:38 p.m.