Triple

T8926187
Position Surface form Disambiguated ID Type / Status
Subject Old Babylonian Empire E212543 entity
Predicate majorRuler P8531 FINISHED
Object Sin-Muballit E565613 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: Sin-Muballit | Statement: [Old Babylonian Empire, majorRuler, Sin-Muballit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sin-Muballit
Context triple: [Old Babylonian Empire, majorRuler, Sin-Muballit]
  • A. Sin-Muballit chosen
    Sin-Muballit was a king of Babylon in the early 18th century BCE and the father of Hammurabi, under whom Babylon’s power and territory began to expand.
  • B. Belal
    Belal is the given name of Belal Muhammad, an American mixed martial artist competing in the UFC welterweight division.
  • C. Abdal
    Abdal are a group of righteous, hidden saints in Islamic mysticism believed to uphold spiritual balance in the world.
  • D. Mirzam
    Mirzam is a bright blue-white giant star in the constellation Canis Major, known as one of the prominent stars near Sirius in the winter sky.
  • E. Abu Lulu
    Abu Lulu was a Persian slave and craftsman historically known for assassinating the second Rashidun caliph, Umar ibn al-Khattab, in 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_69ca839481d48190b42b037e0d0f636c completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66700fb48190874563e535f20437 completed April 1, 2026, 12:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba58e9ec81909141c516d05ac790 completed April 3, 2026, 1:02 p.m.
Created at: March 30, 2026, 6:57 p.m.