Triple

T22666734
Position Surface form Disambiguated ID Type / Status
Subject Diocese of Moesia E559810 entity
Predicate hasCapital P204 FINISHED
Object Serdica 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: Serdica | Statement: [Diocese of Moesia, hasCapital, Serdica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Serdica
Context triple: [Diocese of Moesia, hasCapital, Serdica]
  • A. Serdica chosen
    Serdica was an important ancient Roman city in the province of Thracia, located on the site of present-day Sofia, Bulgaria.
  • B. Serdika
    Serdika is the ancient name of the city now known as Sofia, the capital of Bulgaria, historically significant as a major Roman and Byzantine urban center in the Balkans.
  • C. Serdinya
    Serdinya is a small commune in the Pyrénées-Orientales department of southern France, situated in the historic region of Conflent in the eastern Pyrenees.
  • D. Euxinograd
    Euxinograd is a former royal summer residence and seaside palace complex on the Black Sea coast near Varna, Bulgaria.
  • E. Kaliakra
    Kaliakra is a historic fortified headland and medieval port on Bulgaria’s Black Sea coast, renowned for its strategic cliffs and archaeological remains.
  • 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1781c2c808190baf6964ca1eced6f completed April 29, 2026, 3:16 a.m.
Created at: April 17, 2026, 3:09 p.m.