Triple

T8860297
Position Surface form Disambiguated ID Type / Status
Subject Dacia Ripensis E210868 entity
Predicate hadFort P3479 FINISHED
Object Oescus E211819 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: Oescus | Statement: [Dacia Ripensis, hadFort, Oescus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oescus
Context triple: [Dacia Ripensis, hadFort, Oescus]
  • A. Oescus chosen
    Oescus was an important ancient Roman city and military base in the province of Moesia, located near the Danube River in what is now northern Bulgaria.
  • B. Arakoon
    Arakoon is a small coastal locality in New South Wales, Australia, known for its beaches and the historic Trial Bay Gaol.
  • C. Hebrus
    Hebrus is the ancient name of the Maritsa River, a major waterway flowing through the Balkans in Southeast Europe.
  • D. Aesernia
    Aesernia was an important ancient town of the Samnite people in south-central Italy, later becoming a Roman colony.
  • E. Nisaea
    Nisaea was the port town and harbor of ancient Megara in Greece, serving as its main maritime outlet on the Saronic Gulf.
  • 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_69ca838bbddc8190ab546d737e5d350f completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60e712d08190bfb1c4ba3acaea90 completed April 1, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfa0b94f5481909902b5fa405a502f completed April 3, 2026, 11:12 a.m.
Created at: March 30, 2026, 6:50 p.m.