Triple

T11737929
Position Surface form Disambiguated ID Type / Status
Subject Bioko Norte E279077 entity
Predicate locatedOnIsland P970 FINISHED
Object Bioko E34267 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: Bioko | Statement: [Bioko Norte, locatedOnIsland, Bioko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bioko
Context triple: [Bioko Norte, locatedOnIsland, Bioko]
  • A. Bioko Island chosen
    Bioko Island is a volcanic island off the west coast of Africa that forms the northern region of Equatorial Guinea and hosts the country’s capital, Malabo.
  • B. Bioko Norte
    Bioko Norte is a province of Equatorial Guinea that occupies the northern part of Bioko Island and includes the national capital, Malabo.
  • C. Annobón
    Annobón is a small, remote volcanic island and province of Equatorial Guinea in the Gulf of Guinea, known for its unique biodiversity and Portuguese-influenced Creole culture.
  • D. São Tomé
    São Tomé is the largest city and main economic and administrative center of the island nation of São Tomé and Príncipe in the Gulf of Guinea.
  • E. Ibo Island
    Ibo Island is a historic island in northern Mozambique known for its centuries-old Swahili, Arab, and Portuguese influences, colonial architecture, and role as a former trading post.
  • 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_69d6aaffec6881908bead509e8621742 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4ef1c4881909ad36dc27b1fe193 completed April 10, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69f5f63477e08190957dd1ef709fe93b completed May 2, 2026, 1:03 p.m.
Created at: April 8, 2026, 9:41 p.m.