Triple

T19716889
Position Surface form Disambiguated ID Type / Status
Subject Mygdonia E473500 entity
Predicate borders P224 FINISHED
Object Bisaltia 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: Bisaltia | Statement: [Mygdonia, borders, Bisaltia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bisaltia
Context triple: [Mygdonia, borders, Bisaltia]
  • A. Bisaltia chosen
    Bisaltia was an ancient region in northern Greece, historically inhabited by the Thracian Bisaltae and later incorporated into the Macedonian kingdom.
  • B. Hecatompylos
    Hecatompylos was an ancient Iranian city of strategic importance that served as a major royal residence and administrative center in the Hellenistic and early Parthian periods.
  • C. Omonoia
    Omonoia is a central and historically significant square and transport hub in Athens, Greece, known for its busy urban atmosphere and commercial activity.
  • D. Belas
    Belas is a rapidly developing urban municipality in Luanda Province, Angola, known for its residential expansion and emerging commercial infrastructure.
  • E. Belas
    Belas is a civil parish in the municipality of Sintra, Portugal, known for its historic village center and proximity to Lisbon.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6440d96288190bfb732d2f8ceac79 completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.