Triple

T16044276
Position Surface form Disambiguated ID Type / Status
Subject Government of Eritrea E389175 entity
Predicate capital P234 FINISHED
Object Asmara E92266 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: Asmara | Statement: [Government of Eritrea, capital, Asmara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Asmara
Context triple: [Government of Eritrea, capital, Asmara]
  • A. Asmara chosen
    Asmara is the largest city of Eritrea, known for its well-preserved Italian colonial modernist architecture and status as a UNESCO World Heritage Site.
  • B. Massawa
    Massawa is a historic Eritrean port city on the Red Sea, known for its strategic maritime location and Ottoman- and Italian-influenced architecture.
  • C. Mekele
    Mekele is the capital city of Ethiopia’s Tigray Region and a major political, economic, and cultural center in the country’s north.
  • D. Awasa
    Awasa is a city in southern Ethiopia, known as the capital of the Sidama Region and a hub by Lake Awasa.
  • E. Djibouti City
    Djibouti City is the largest urban center and main economic, political, and cultural hub of the Republic of Djibouti, located on the Gulf of Tadjoura in the Horn of Africa.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1835d1dac819089abec9f0668ec78 completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb893f988190a0693564bbe78ca1 completed May 10, 2026, 2:20 a.m.
Created at: April 10, 2026, 4:56 a.m.