Triple

T15836614
Position Surface form Disambiguated ID Type / Status
Subject Somaliland forces E384000 entity
Predicate controls P760 FINISHED
Object Berbera E117160 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: Berbera | Statement: [Somaliland forces, controls, Berbera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berbera
Context triple: [Somaliland forces, controls, Berbera]
  • A. Berbera chosen
    Berbera is a major port city on the Gulf of Aden in Somaliland, serving as a key maritime hub for trade in the Horn of Africa.
  • B. Banyole
    The Banyole are a Bantu-speaking ethnic group in eastern Uganda known for their agricultural livelihoods, clan-based social structure, and rich oral traditions.
  • C. Melesse
    Melesse is a commune in the Ille-et-Vilaine department of Brittany in northwestern France.
  • D. Hadrut
    Hadrut is a town in the Nagorno-Karabakh region, historically part of the Shusha uezd, known for its strategic location and role in regional conflicts between Armenia and Azerbaijan.
  • E. Bologhine
    Bologhine is a coastal district of Algiers, Algeria, known for its historic neighborhoods and proximity to the Mediterranean Sea.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e1fcd48190bcb884f6c65db847 completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa13a83448190adcad8bb84622e55 completed May 9, 2026, 9:03 p.m.
Created at: April 10, 2026, 4:49 a.m.