Triple

T14788770
Position Surface form Disambiguated ID Type / Status
Subject Denkyira E347597 entity
Predicate capital P234 FINISHED
Object Jukwa
Jukwa is a town in Ghana that historically served as the capital of the Denkyira kingdom.
 E1120102 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: Jukwa | Statement: [Denkyira, capital, Jukwa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jukwa
Context triple: [Denkyira, capital, Jukwa]
  • A. Jaku
    Jaku is a lesser-known Bantu language belonging to the Jarawan subgroup, spoken by a small community in West Africa.
  • B. Jemulpo
    Jemulpo is the former name of the port city now known as Incheon in South Korea, historically significant as a major gateway for international trade and foreign contact.
  • C. Jajaghu
    Jajaghu is an alternative name for the Jago Temple, an ancient religious structure in Indonesia known for its historical and architectural significance.
  • D. Ba'ku
    The Ba'ku are a peaceful, long-lived humanoid species in the Star Trek universe who inhabit a secluded planet with regenerative properties and reject advanced technology in favor of a simple, agrarian lifestyle.
  • E. Nokk
    Nokk is a mythical water spirit from Scandinavian folklore, often depicted as a shape-shifting creature that lures people into lakes and rivers.
  • 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: Jukwa
Triple: [Denkyira, capital, Jukwa]
Generated description
Jukwa is a town in Ghana that historically served as the capital of the Denkyira kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jukwa
Target entity description: Jukwa is a town in Ghana that historically served as the capital of the Denkyira kingdom.
  • A. Jaku
    Jaku is a lesser-known Bantu language belonging to the Jarawan subgroup, spoken by a small community in West Africa.
  • B. Jemulpo
    Jemulpo is the former name of the port city now known as Incheon in South Korea, historically significant as a major gateway for international trade and foreign contact.
  • C. Jajaghu
    Jajaghu is an alternative name for the Jago Temple, an ancient religious structure in Indonesia known for its historical and architectural significance.
  • D. Ba'ku
    The Ba'ku are a peaceful, long-lived humanoid species in the Star Trek universe who inhabit a secluded planet with regenerative properties and reject advanced technology in favor of a simple, agrarian lifestyle.
  • E. Nokk
    Nokk is a mythical water spirit from Scandinavian folklore, often depicted as a shape-shifting creature that lures people into lakes and rivers.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decaa1e9ec81908d7c26c1c4e43014 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24bc8464819096b019f1e927d1a9 completed May 8, 2026, 6 p.m.
NEDg Description generation batch_69fe27e699688190952b6a4b922e3294 completed May 8, 2026, 6:13 p.m.
NED2 Entity disambiguation (via description) batch_69fe2896057881908b3947d9649739e7 completed May 8, 2026, 6:16 p.m.
Created at: April 10, 2026, 1:31 a.m.