Triple

T1992322
Position Surface form Disambiguated ID Type / Status
Subject Susanna E43277 entity
Predicate setting P1957 FINISHED
Object Babylon E23692 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: Babylon | Statement: [Susanna, setting, Babylon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Babylon
Context triple: [Susanna, setting, Babylon]
  • A. Babylon
    Babylon is a town on the South Shore of Long Island in New York, known for its suburban communities, waterfront access, and role as a transportation hub.
  • B. Babylon chosen
    Babylon was an ancient Mesopotamian city-state and imperial capital renowned for its monumental architecture, advanced culture, and central role in Near Eastern history and biblical tradition.
  • C. Ashur
    Ashur is an ancient Mesopotamian city in northern Iraq that served as the first capital and religious center of the Assyrian Empire.
  • D. Nippur
    Nippur was an ancient Sumerian city in Mesopotamia that served as a major religious center dedicated to the god Enlil.
  • E. Sippar
    Sippar was an important ancient Mesopotamian city, renowned as a religious and administrative center particularly associated with the sun god Shamash.
  • 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_69a88714cf2c819081644be450b8356e completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb846f1c0819081edd8d5eb59adce completed March 7, 2026, 5:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0ad7c254819091159c5362e7a293 completed March 8, 2026, 11:48 p.m.
Created at: March 4, 2026, 7:37 p.m.