Triple

T5746053
Position Surface form Disambiguated ID Type / Status
Subject Port of İzmit E126734 entity
Predicate isOnTradeRoute P62174 FINISHED
Object Black Sea–Mediterranean maritime route E485955 NE FINISHED

How this triple was built (3 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: Black Sea–Mediterranean maritime route | Statement: [Port of İzmit, isOnTradeRoute, Black Sea–Mediterranean maritime route]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Black Sea–Mediterranean maritime route
Context triple: [Port of İzmit, isOnTradeRoute, Black Sea–Mediterranean maritime route]
  • A. Red Sea–Mediterranean–Indian Ocean shipping route
    The Red Sea–Mediterranean–Indian Ocean shipping route is a major global maritime corridor linking Europe, Asia, and East Africa via the Suez Canal and adjacent seas, carrying a significant share of the world’s container and energy trade.
  • B. Baltic Sea trade routes
    The Baltic Sea trade routes were a network of maritime and riverine pathways that connected the cities and ports of Northern and Eastern Europe, facilitating extensive commerce in goods like furs, grain, and timber and linking regions such as the Novgorod Republic with the wider Hanseatic trading world.
  • C. Mediterranean trade routes
    Mediterranean trade routes were a network of maritime and coastal pathways that connected Europe, North Africa, and the Near East, facilitating extensive commercial, cultural, and disease transmission across the Mediterranean Sea.
  • D. Black Sea trade network chosen
    The Black Sea trade network was a vital medieval maritime and overland commercial system linking Europe, the Near East, and Central Asia through ports and routes around the Black Sea.
  • E. White Sea trade route
    The White Sea trade route was a key maritime and riverine corridor in northern Russia that linked inland centers like Kholmogory to Arctic ports, facilitating early Russian trade with Western Europe.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isOnTradeRoute
Context triple: [Port of İzmit, isOnTradeRoute, Black Sea–Mediterranean maritime route]
  • A. includesTradeRoute
    Indicates that one entity contains, encompasses, or makes use of a particular trade route within its scope or structure.
  • B. isOnFreightRoute
    Indicates that something lies along or is included within a designated freight transportation route used for moving goods.
  • C. hasSeaRouteConnection
    Indicates that there exists a navigable maritime route linking two locations or entities.
  • D. associatedWithSeaRoute chosen
    Indicates a relationship where something is connected or related to a particular sea route, such as by use, location, or relevance.
  • E. servesAsCargoHubFor
    Indicates that one entity functions as a central location or facility for handling, consolidating, and distributing cargo associated with another entity.
  • F. None of above.

Provenance (4 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_69c0083179548190b384b0bf3c08ca4d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b52663c8190ab44258468d4296d completed March 22, 2026, 5:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e2c54c0819087ab79ae855b9677 completed March 22, 2026, 11:41 p.m.
PD Predicate disambiguation batch_69c021ca61688190875bd6107161c284 completed March 22, 2026, 5:07 p.m.
Created at: March 22, 2026, 3:48 p.m.