Triple

T14818769
Position Surface form Disambiguated ID Type / Status
Subject Cuanza Sul Province E348387 entity
Predicate hasCapital P204 FINISHED
Object Sumbe
Sumbe is a coastal city in western Angola that serves as an important administrative and economic center in the Cuanza Sul region.
 E1121559 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: Sumbe | Statement: [Cuanza Sul Province, hasCapital, Sumbe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sumbe
Context triple: [Cuanza Sul Province, hasCapital, Sumbe]
  • A. Susima
    Susima was an ancient Indian prince of the Maurya dynasty, known primarily as the elder son of Emperor Bindusara and rival claimant to the throne against his brother Ashoka.
  • B. Kumiya
    Kumiya is a Berber tribal group historically associated with the rise and support base of the Almohad leader Abd al-Mu’min in the Maghreb.
  • C. Sannomiya
    Sannomiya is a major commercial and transportation hub in central Kobe, Japan, known for its shopping streets, nightlife, and role as the city’s downtown core.
  • D. Susuman
    Susuman is a small mining town in Russia's Magadan Oblast, located in the remote Russian Far East.
  • E. Sameba
    Sameba is the monumental main cathedral of the Georgian Orthodox Church in Tbilisi, renowned as one of the largest religious buildings in the Caucasus.
  • 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: Sumbe
Triple: [Cuanza Sul Province, hasCapital, Sumbe]
Generated description
Sumbe is a coastal city in western Angola that serves as an important administrative and economic center in the Cuanza Sul region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sumbe
Target entity description: Sumbe is a coastal city in western Angola that serves as an important administrative and economic center in the Cuanza Sul region.
  • A. Susima
    Susima was an ancient Indian prince of the Maurya dynasty, known primarily as the elder son of Emperor Bindusara and rival claimant to the throne against his brother Ashoka.
  • B. Kumiya
    Kumiya is a Berber tribal group historically associated with the rise and support base of the Almohad leader Abd al-Mu’min in the Maghreb.
  • C. Sannomiya
    Sannomiya is a major commercial and transportation hub in central Kobe, Japan, known for its shopping streets, nightlife, and role as the city’s downtown core.
  • D. Susuman
    Susuman is a small mining town in Russia's Magadan Oblast, located in the remote Russian Far East.
  • E. Sameba
    Sameba is the monumental main cathedral of the Georgian Orthodox Church in Tbilisi, renowned as one of the largest religious buildings in the Caucasus.
  • 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.