Triple

T16794589
Position Surface form Disambiguated ID Type / Status
Subject Northern Region of Ghana E408199 entity
Predicate contains P35 FINISHED
Object Savelugu
Savelugu is a town and district capital in northern Ghana known as an important local center for agriculture and trade.
 E1233703 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: Savelugu | Statement: [Northern Region of Ghana, contains, Savelugu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Savelugu
Context triple: [Northern Region of Ghana, contains, Savelugu]
  • A. Luga
    Luga is a small historic town in northwestern Russia known for its strategic location and role in regional transport and industry.
  • B. Lugana
    Lugana is an Italian white wine appellation near Lake Garda, renowned for its fresh, mineral-driven wines primarily made from the Turbiana grape.
  • C. Resava
    Resava is a river in central Serbia known for flowing through a karst region that includes the famous Resava Cave before joining the Velika Morava.
  • D. Zavalita
    Zavalita is the disillusioned journalist and central protagonist of Mario Vargas Llosa’s novel "Conversation in the Cathedral," whose reflections expose the moral and political decay of mid-20th-century Peru.
  • E. Lokuta
    Lokuta is a small village located in Järva County in central Estonia.
  • 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: Savelugu
Triple: [Northern Region of Ghana, contains, Savelugu]
Generated description
Savelugu is a town and district capital in northern Ghana known as an important local center for agriculture and trade.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Savelugu
Target entity description: Savelugu is a town and district capital in northern Ghana known as an important local center for agriculture and trade.
  • A. Luga
    Luga is a small historic town in northwestern Russia known for its strategic location and role in regional transport and industry.
  • B. Lugana
    Lugana is an Italian white wine appellation near Lake Garda, renowned for its fresh, mineral-driven wines primarily made from the Turbiana grape.
  • C. Resava
    Resava is a river in central Serbia known for flowing through a karst region that includes the famous Resava Cave before joining the Velika Morava.
  • D. Zavalita
    Zavalita is the disillusioned journalist and central protagonist of Mario Vargas Llosa’s novel "Conversation in the Cathedral," whose reflections expose the moral and political decay of mid-20th-century Peru.
  • E. Lokuta
    Lokuta is a small village located in Järva County in central Estonia.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a8b66c8190b83d8af85d2b23a8 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab0e1e9c8190bb2ef0825b25f6e5 completed May 10, 2026, 3:58 p.m.
NEDg Description generation batch_6a00ac1d18c08190969108e567d6eced completed May 10, 2026, 4:02 p.m.
NED2 Entity disambiguation (via description) batch_6a00acc3a9dc819087e07e539760bf34 completed May 10, 2026, 4:05 p.m.
Created at: April 10, 2026, 5:22 a.m.