Triple

T19156907
Position Surface form Disambiguated ID Type / Status
Subject Équateur Province E468948 entity
Predicate hasCity P316 FINISHED
Object Boende
Boende is a town and river port in the central Democratic Republic of the Congo, serving as an administrative and commercial center in the Équateur region.
 E799133 NE FINISHED

How this triple was built (4 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: Boende | Statement: [Équateur Province, hasCity, Boende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Boende
Context triple: [Équateur Province, hasCity, Boende]
  • A. Boende
    Boende is a town in the Democratic Republic of the Congo that serves as an important local center of trade and administration in the Tshuapa Province.
  • B. Haus
    Haus is a village in Osterøy Municipality in Vestland county, Norway, situated on the island of Osterøy.
  • C. Rom Eiendom
    Rom Eiendom is a Norwegian real estate company that manages and develops properties associated with the country’s railway infrastructure.
  • D. Bygding
    A Bygding is a resident or native of the Norwegian municipality of Bygland in Agder county.
  • E. Häuser
    Häuser is a photographic series by German artist Thomas Ruff featuring large-format, deadpan images of suburban and urban building facades that explore architecture, anonymity, and the nature of photographic representation.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Boende
Triple: [Équateur Province, hasCity, Boende]
Generated description
Boende is a town and river port in the central Democratic Republic of the Congo, serving as an administrative and commercial center in the Équateur region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Boende
Target entity description: Boende is a town and river port in the central Democratic Republic of the Congo, serving as an administrative and commercial center in the Équateur region.
  • A. Boende chosen
    Boende is a town in the Democratic Republic of the Congo that serves as an important local center of trade and administration in the Tshuapa Province.
  • B. Haus
    Haus is a village in Osterøy Municipality in Vestland county, Norway, situated on the island of Osterøy.
  • C. Rom Eiendom
    Rom Eiendom is a Norwegian real estate company that manages and develops properties associated with the country’s railway infrastructure.
  • D. Bygding
    A Bygding is a resident or native of the Norwegian municipality of Bygland in Agder county.
  • E. Häuser
    Häuser is a photographic series by German artist Thomas Ruff featuring large-format, deadpan images of suburban and urban building facades that explore architecture, anonymity, and the nature of photographic representation.
  • F. None of above.

Provenance (5 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb9cf9081908b17073755e83554 completed April 20, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a06f258c5a0819084921b6e44bf1b34 completed May 15, 2026, 10:15 a.m.
NEDg Description generation batch_6a06f41269748190b6fa6301d8eb4f4f completed May 15, 2026, 10:23 a.m.
NED2 Entity disambiguation (via description) batch_6a06f4da6b04819084dab89e9b3c5d3e completed May 15, 2026, 10:26 a.m.
Created at: April 10, 2026, 12:06 p.m.