Triple

T18200670
Position Surface form Disambiguated ID Type / Status
Subject Beroea E435773 entity
Predicate country P26 FINISHED
Object Ancient Macedonia NE NERFINISHED

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: Ancient Macedonia | Statement: [Beroea, country, Ancient Macedonia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ancient Macedonia
Context triple: [Beroea, country, Ancient Macedonia]
  • A. Macedon chosen
    Macedon was an ancient kingdom in the northern Greek peninsula that rose to prominence under Philip II and his son Alexander the Great, becoming the center of a vast empire.
  • B. Achaean Greece
    Achaean Greece refers to the Mycenaean-era Greek world of powerful palace-states and warrior-kings that forms the main Greek side in the legendary Trojan War tradition.
  • C. Sparta
    Sparta was a prominent ancient Greek city-state known for its militaristic society, rigorous citizen training, and dominant land-based army.
  • D. Sparta
    Sparta is a budget-oriented AMD Sempron processor core designed for entry-level desktop computing.
  • E. Sparta
    Sparta is a historic village in Elgin County, Ontario, known for its 19th-century heritage buildings and roots as a Quaker settlement.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d610f88190b4f69b1c433ea6b1 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.