Triple

T12071667
Position Surface form Disambiguated ID Type / Status
Subject Zaire 74 E287438 entity
Predicate city P40 FINISHED
Object Kinshasa E54433 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: Kinshasa | Statement: [Zaire 74, city, Kinshasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kinshasa
Context triple: [Zaire 74, city, Kinshasa]
  • A. Kinshasa chosen
    Kinshasa is the largest city and political, economic, and cultural center of the Democratic Republic of the Congo, located along the Congo River in Central Africa.
  • B. Brazzaville
    Brazzaville is the capital and largest city of the Republic of the Congo, located on the Congo River directly across from Kinshasa in Central Africa.
  • C. Luanda
    Luanda is the capital and largest city of Angola, a major Atlantic port and economic hub with a history shaped by Portuguese colonial rule and the transatlantic slave trade.
  • D. Malabo
    Malabo is the largest city and main economic and administrative center of Equatorial Guinea, located on the northern coast of Bioko Island in the Gulf of Guinea.
  • E. Mbandaka
    Mbandaka is a city in the northwestern Democratic Republic of the Congo, located on the Congo River and serving as a regional commercial and administrative center.
  • 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_69d6ab4846e081908ee7bbd66a6d3459 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9045a507081909070ea37173d6f97 completed April 10, 2026, 2:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69f70a114ccc81909bc428c40c01a461 completed May 3, 2026, 8:40 a.m.
Created at: April 8, 2026, 9:48 p.m.