Triple

T15182507
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Thrace E362778 entity
Predicate hasPortCity P2745 FINISHED
Object Perinthus E345671 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: Perinthus | Statement: [Kingdom of Thrace, hasPortCity, Perinthus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perinthus
Context triple: [Kingdom of Thrace, hasPortCity, Perinthus]
  • A. Perinthus chosen
    Perinthus was an ancient Greek city in Thrace that became an important regional center and later a prominent Roman provincial capital.
  • B. Olynthus
    Olynthus was an important ancient Greek city in the Chalcidice region, known for its strategic location and well-preserved classical-era urban planning and mosaics.
  • C. Eleutherae
    Eleutherae was an ancient Greek city on the border between Attica and Boeotia, known for its sanctuary of Dionysus and its strategic location near Mount Cithaeron.
  • D. 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.
  • E. Troesmis
    Troesmis was an ancient Roman military and urban settlement in the province of Moesia, strategically located near the Danube River in what is now Romania.
  • 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_69d85a09a39c81908759f23268e2d408 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006663ad48190986b680001be0e9b completed April 15, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fec89210e081909e8077fa2487c40e completed May 9, 2026, 5:39 a.m.
Created at: April 10, 2026, 3:09 a.m.