Triple

T5432147
Position Surface form Disambiguated ID Type / Status
Subject Epirote League E121520 entity
Predicate capital P234 FINISHED
Object Ambracia E298182 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: Ambracia | Statement: [Epirote League, capital, Ambracia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambracia
Context triple: [Epirote League, capital, Ambracia]
  • A. Ambracia chosen
    Ambracia was an ancient Greek city in Epirus that became an important regional center and later the capital of King Pyrrhus.
  • B. Aegium
    Aegium was an important ancient Greek city in the region of Achaea, known as a political and religious center, especially during the Hellenistic period.
  • C. Ascra
    Ascra was an ancient village in Boeotia, Greece, best known as the hometown of the poet Hesiod.
  • D. Amaseia
    Amaseia was an ancient city in northern Anatolia that served as the early capital of the Kingdom of Pontus and an important regional political and cultural center.
  • E. Epidamnos
    Epidamnos was an ancient Greek colony on the Adriatic coast, located where the modern Albanian city of Durrës now stands.
  • 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_69bd463c65f0819082ee6483ab4b466a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd883f982c8190bdf277e1ba85ff7b completed March 20, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf41284998819096667ae70180e067 completed March 22, 2026, 1:08 a.m.
Created at: March 20, 2026, 2:06 p.m.