Triple

T21092146
Position Surface form Disambiguated ID Type / Status
Subject Gulf of Guinea Creoles E519662 entity
Predicate hasMember P10 FINISHED
Object Santome NE NERFINISHED

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: Santome | Statement: [Gulf of Guinea Creoles, hasMember, Santome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Santome
Context triple: [Gulf of Guinea Creoles, hasMember, Santome]
  • A. São Tomé chosen
    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.
  • B. 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.
  • C. Bioko Island
    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.
  • D. Somorika
    Somorika is a rural community in Akoko-Edo Local Government Area of Edo State, Nigeria, known for its scenic rocky landscape and traditional cultural heritage.
  • E. Fernando Poo
    Fernando Poo is the former colonial name for Bioko, an island in Equatorial Guinea located in the Gulf of Guinea off the west coast of Africa.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094f6ebc8190a90b014755a9d4a6 completed April 21, 2026, 5:21 a.m.
Created at: April 16, 2026, 2:51 p.m.