Triple

T20228451
Position Surface form Disambiguated ID Type / Status
Subject Perdiccas II of Macedon E495452 entity
Predicate capital P234 FINISHED
Object Aegae 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: Aegae | Statement: [Perdiccas II of Macedon, capital, Aegae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aegae
Context triple: [Perdiccas II of Macedon, capital, Aegae]
  • A. Aegae chosen
    Aegae was the ancient royal city of Macedon and the original seat of the Argead dynasty, known for its palace complex and royal tombs.
  • B. Istros
    Istros was an important ancient Greek colony on the western coast of the Black Sea, serving as a major commercial and cultural hub in the region.
  • C. Evrostina
    Evrostina is a village in the Corinthia region of the Peloponnese in Greece, known for its mountainous landscape and traditional character.
  • D. Efkarpia
    Efkarpia is a suburban municipal unit in the Thessaloniki urban area of northern Greece, forming part of the Municipality of Pavlos Melas.
  • E. Cibyrrha
    Cibyrrha was an ancient coastal city in southwestern Asia Minor, known primarily as the namesake of the Byzantine Cibyrrhaeot naval theme.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fdb61b08190b850a9648ebfb720 completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.