Triple

T17583221
Position Surface form Disambiguated ID Type / Status
Subject Eucratides I E428254 entity
Predicate capital P234 FINISHED
Object Bactra 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: Bactra | Statement: [Eucratides I, capital, Bactra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bactra
Context triple: [Eucratides I, capital, Bactra]
  • A. Bactra chosen
    Bactra is the ancient name of Balkh, a historically significant city in northern Afghanistan that was a major center of trade, culture, and religion along the Silk Road.
  • B. Panticapaeum
    Panticapaeum was an important ancient Greek city and trading center on the Cimmerian Bosporus, located where the modern city of Kerch in Crimea now stands.
  • C. Tushpa
    Tushpa was the ancient fortified city on the eastern shore of Lake Van that served as the political and cultural center of the Kingdom of Urartu in the early first millennium BCE.
  • D. Gândaras
    Gândaras is a civil parish located in the municipality of Lousã in central Portugal.
  • E. Selymbria
    Selymbria was an ancient Greek colony on the Propontis (Sea of Marmara), known as a coastal city strategically located near the later site of Constantinople.
  • 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_69d889e1030481909950e140c63255b9 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e463cf556881908d2935b3761f65df completed April 19, 2026, 5:10 a.m.
Created at: April 10, 2026, 5:50 a.m.