Triple

T960447
Position Surface form Disambiguated ID Type / Status
Subject Red Sea E20723 entity
Predicate borderedBy P224 FINISHED
Object Eritrea E16113 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: Eritrea | Statement: [Red Sea, borderedBy, Eritrea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eritrea
Context triple: [Red Sea, borderedBy, Eritrea]
  • A. Eritrea chosen
    Eritrea is a country in the Horn of Africa known for its Red Sea coastline, diverse ethnic groups, and complex political history since gaining independence from Ethiopia in 1993.
  • B. Ethiopia
    Ethiopia is a landlocked country in the Horn of Africa known for its ancient civilizations, unique cultural heritage, and status as one of the few African nations to largely resist long-term European colonization.
  • C. Djibouti
    Djibouti is a small Horn of Africa nation on the Red Sea and Gulf of Aden, known for its strategic maritime location, diverse ethnic makeup, and role as a hub for foreign military bases.
  • D. Afar
    Afar is a Cushitic language spoken primarily by the Afar people in the Horn of Africa, especially in Djibouti, Ethiopia, and Eritrea.
  • E. Hirshabelle
    Hirshabelle is a federal member state in central Somalia formed from parts of the Hiiraan and Middle Shabelle regions.
  • 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_69a493b21f2881908132dcf45dcd2f36 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b4144c208190980936347a95e233 completed March 1, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad36f094888190b3ccb2acb266941c completed March 8, 2026, 8:44 a.m.
Created at: March 1, 2026, 7:40 p.m.