Triple

T10397377
Position Surface form Disambiguated ID Type / Status
Subject Senusret II E245054 entity
Predicate mother P120 FINISHED
Object Senet E702097 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: Senet | Statement: [Senusret II, mother, Senet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Senet
Context triple: [Senusret II, mother, Senet]
  • A. Kalah
    Kalah is the ancient Assyrian city of Nimrud, a major archaeological site in modern-day Iraq that served as a prominent capital of the Neo-Assyrian Empire.
  • B. Mankal
    Mankal was the original settlement that later developed into the historic Golconda Fort area near Hyderabad in India.
  • C. The Royal Game
    The Royal Game is a psychological novella by Stefan Zweig that explores obsession, isolation, and the mental strains of chess under totalitarian oppression.
  • D. Tentyris
    Tentyris is the ancient Greek name for the Egyptian city of Dendera, renowned for its well-preserved temple complex dedicated primarily to the goddess Hathor.
  • E. Backgammon chosen
    Backgammon is an ancient two-player board game of strategy and chance in which players race their checkers around and off a board according to dice rolls.
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9d0de448190b0bfd4d6c87d47fa completed April 7, 2026, 11:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fbbad25081908712601404734988 completed April 9, 2026, 7:19 p.m.
Created at: April 6, 2026, 12:07 p.m.