Triple

T3963863
Position Surface form Disambiguated ID Type / Status
Subject Harun E85968 entity
Predicate brotherOf P363 FINISHED
Object Moses E11297 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: Moses | Statement: [Harun, brotherOf, Moses]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moses
Context triple: [Harun, brotherOf, Moses]
  • A. Moses chosen
    Moses is a central prophet and leader in the Hebrew Bible, traditionally credited with leading the Israelites out of Egypt and receiving the Ten Commandments from God.
  • B. Mose
    Mose is a minor character in Harriet Beecher Stowe’s novel "Uncle Tom’s Cabin," depicted as one of Uncle Tom’s children within the enslaved family central to the story.
  • C. Moses the Black
    Moses the Black was a 4th-century Ethiopian desert monk and former bandit who became a renowned Christian ascetic and saint among the Desert Fathers.
  • D. Yoshua
    Yoshua is a male given name most notably borne by Yoshua Bengio, a pioneering Canadian computer scientist and deep learning researcher.
  • E. Matan Torah
    Matan Torah is the Jewish term for the divine giving of the Torah to the Israelites, traditionally understood to have occurred at Mount Sinai.
  • 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_69aed93a96908190bcbdbfa718f155bd completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef97326888190bbfe15b218e3112e completed March 9, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533bb92088190b7d0ba2eb92c3e80 completed March 14, 2026, 10:08 a.m.
Created at: March 9, 2026, 3:31 p.m.