Triple

T24185579
Position Surface form Disambiguated ID Type / Status
Subject Emirate of Harar E599546 entity
Predicate tradeLinksWith P23353 FINISHED
Object Red Sea ports LITERAL 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: Red Sea ports | Statement: [Emirate of Harar, tradeLinksWith, Red Sea ports]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: tradeLinksWith
Context triple: [Emirate of Harar, tradeLinksWith, Red Sea ports]
  • A. tradeNetwork chosen
    Indicates a relationship where entities are connected through the exchange of goods, services, or resources within an ongoing system of trade.
  • B. relatedExchange
    Indicates that there is a connection or association between two exchanges or exchange-related events.
  • C. tradeHubWith
    Indicates that one entity functions as a central location or node for trading activities in connection with another entity.
  • D. externalRelations
    Indicates that an entity has relationships, interactions, or connections with entities outside its own immediate group, system, or organization.
  • E. tradedAlong
    Indicates that an entity engaged in trade or exchange activities following or using a particular route, path, or corridor.
  • F. None of above.

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_69e288cdc8b88190bf2f835d3cb4ca28 completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f27c9ddfcc819096697a844b300cce completed April 29, 2026, 9:48 p.m.
PD Predicate disambiguation batch_69f1c42f942c8190b103ff29a60fef34 completed April 29, 2026, 8:41 a.m.
Created at: April 17, 2026, 11:35 p.m.