Triple

T14818803
Position Surface form Disambiguated ID Type / Status
Subject Cuanza Sul Province E348387 entity
Predicate hasMunicipality P847 FINISHED
Object Porto Amboim
Porto Amboim is a coastal municipality and port town in western Angola known for its role in regional fishing and maritime trade.
E1121567 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: Porto Amboim | Statement: [Cuanza Sul Province, hasMunicipality, Porto Amboim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porto Amboim
Context triple: [Cuanza Sul Province, hasMunicipality, Porto Amboim]
  • A. Lourenço Marques
    Lourenço Marques is the former name of Maputo, the capital city and main port of Mozambique.
  • B. Beira
    Beira is a major port city in central Mozambique, serving as a key commercial and transport hub for the region.
  • C. Margão
    Margão is a major commercial and cultural city in the South Goa district of the Indian state of Goa.
  • D. Mindelo
    Mindelo is the main port city and cultural hub of the Cape Verdean island of São Vicente, known for its vibrant music scene and colorful colonial architecture.
  • E. Macapá
    Macapá is a Brazilian city located on the northern bank of the Amazon River, known for being one of the few state capitals in the world situated directly on the equator.
  • 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: Porto Amboim
Triple: [Cuanza Sul Province, hasMunicipality, Porto Amboim]
Generated description
Porto Amboim is a coastal municipality and port town in western Angola known for its role in regional fishing and maritime trade.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Porto Amboim
Target entity description: Porto Amboim is a coastal municipality and port town in western Angola known for its role in regional fishing and maritime trade.
  • A. Lourenço Marques
    Lourenço Marques is the former name of Maputo, the capital city and main port of Mozambique.
  • B. Beira
    Beira is a major port city in central Mozambique, serving as a key commercial and transport hub for the region.
  • C. Margão
    Margão is a major commercial and cultural city in the South Goa district of the Indian state of Goa.
  • D. Mindelo
    Mindelo is the main port city and cultural hub of the Cape Verdean island of São Vicente, known for its vibrant music scene and colorful colonial architecture.
  • E. Macapá
    Macapá is a Brazilian city located on the northern bank of the Amazon River, known for being one of the few state capitals in the world situated directly on the equator.
  • F. None of above. chosen

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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe4cf38819090f25ef045351d5d completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389940e081908ad627955cb8d52e completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe3a315d2c81908db44e7792908e39 completed May 8, 2026, 7:32 p.m.
NED2 Entity disambiguation (via description) batch_69fe3bda81cc8190b256ec6284383dde completed May 8, 2026, 7:39 p.m.
Created at: April 10, 2026, 1:50 a.m.