Triple

T16268806
Position Surface form Disambiguated ID Type / Status
Subject Walter Sisulu University E394942 entity
Predicate hasCampusIn P4623 FINISHED
Object Komani
Komani is a town in South Africa’s Eastern Cape province, historically known as Queenstown and serving as a regional educational and commercial hub.
 E1204904 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: Komani | Statement: [Walter Sisulu University, hasCampusIn, Komani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Komani
Context triple: [Walter Sisulu University, hasCampusIn, Komani]
  • A. Kamanje
    Kamanje is a small village and municipality located in Karlovac County in central Croatia, near the Slovenian border.
  • B. Koman
    Koman is a small language family of northeastern Africa whose member languages are spoken primarily in border regions of Ethiopia and Sudan.
  • C. Kumba
    Kumba is a renowned steel roller coaster at Busch Gardens Tampa Bay, famous for its intense inversions and smooth, high-speed layout.
  • D. Kumba
    Kumba is a major town in southwestern Cameroon known as a commercial hub and cultural crossroads where languages like Cameroonian Pidgin English are widely used.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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: Komani
Triple: [Walter Sisulu University, hasCampusIn, Komani]
Generated description
Komani is a town in South Africa’s Eastern Cape province, historically known as Queenstown and serving as a regional educational and commercial hub.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Komani
Target entity description: Komani is a town in South Africa’s Eastern Cape province, historically known as Queenstown and serving as a regional educational and commercial hub.
  • A. Kamanje
    Kamanje is a small village and municipality located in Karlovac County in central Croatia, near the Slovenian border.
  • B. Koman
    Koman is a small language family of northeastern Africa whose member languages are spoken primarily in border regions of Ethiopia and Sudan.
  • C. Kumba
    Kumba is a renowned steel roller coaster at Busch Gardens Tampa Bay, famous for its intense inversions and smooth, high-speed layout.
  • D. Kumba
    Kumba is a major town in southwestern Cameroon known as a commercial hub and cultural crossroads where languages like Cameroonian Pidgin English are widely used.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245ca5c708190a1e98ab37740c032 completed April 17, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f8eac988190bdcba6778fbffd64 completed May 10, 2026, 6:02 a.m.
NEDg Description generation batch_6a00207849608190a767108a5df6ad44 completed May 10, 2026, 6:06 a.m.
NED2 Entity disambiguation (via description) batch_6a0020f37ec08190be6834347dba3455 completed May 10, 2026, 6:08 a.m.
Created at: April 10, 2026, 5:05 a.m.