Triple

T2199768
Position Surface form Disambiguated ID Type / Status
Subject The Smoke that Thunders E50460 entity
Predicate regionLanguageName P15 FINISHED
Object “Mosi-oa-Tunya” in the Lozi language
“Mosi-oa-Tunya” is the Lozi name for Victoria Falls, one of the world’s largest and most famous waterfalls on the Zambezi River between Zambia and Zimbabwe.
E241468 NE FINISHED

How this triple was built (5 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: “Mosi-oa-Tunya” in the Lozi language | Statement: [The Smoke that Thunders, regionLanguageName, “Mosi-oa-Tunya” in the Lozi language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: “Mosi-oa-Tunya” in the Lozi language
Context triple: [The Smoke that Thunders, regionLanguageName, “Mosi-oa-Tunya” in the Lozi language]
  • A. Kiswah
    Kiswah is the ornate black cloth embroidered with Quranic verses that traditionally drapes and adorns the Kaaba in Mecca.
  • B. Mpulungu
    Mpulungu is a Zambian port town that serves as the country’s main access point to Lake Tanganyika and a hub for regional fishing and trade.
  • C. Tshiluba
    Tshiluba is a Bantu language widely spoken in south-central Democratic Republic of the Congo, particularly in the Kasai region.
  • D. Luba
    Luba is a coastal town and important port on the southern part of Bioko Island in Equatorial Guinea.
  • E. Umkhosi Wokweshwama
    Umkhosi Wokweshwama is a traditional Zulu first-fruits harvest festival that reaffirms the king’s authority, ancestral veneration, and communal renewal.
  • 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: “Mosi-oa-Tunya” in the Lozi language
Triple: [The Smoke that Thunders, regionLanguageName, “Mosi-oa-Tunya” in the Lozi language]
Generated description
“Mosi-oa-Tunya” is the Lozi name for Victoria Falls, one of the world’s largest and most famous waterfalls on the Zambezi River between Zambia and Zimbabwe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: “Mosi-oa-Tunya” in the Lozi language
Target entity description: “Mosi-oa-Tunya” is the Lozi name for Victoria Falls, one of the world’s largest and most famous waterfalls on the Zambezi River between Zambia and Zimbabwe.
  • A. Kiswah
    Kiswah is the ornate black cloth embroidered with Quranic verses that traditionally drapes and adorns the Kaaba in Mecca.
  • B. Mpulungu
    Mpulungu is a Zambian port town that serves as the country’s main access point to Lake Tanganyika and a hub for regional fishing and trade.
  • C. Tshiluba
    Tshiluba is a Bantu language widely spoken in south-central Democratic Republic of the Congo, particularly in the Kasai region.
  • D. Luba
    Luba is a coastal town and important port on the southern part of Bioko Island in Equatorial Guinea.
  • E. Umkhosi Wokweshwama
    Umkhosi Wokweshwama is a traditional Zulu first-fruits harvest festival that reaffirms the king’s authority, ancestral veneration, and communal renewal.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regionLanguageName
Context triple: [The Smoke that Thunders, regionLanguageName, “Mosi-oa-Tunya” in the Lozi language]
  • A. regionLanguage
    Indicates that a particular language is used or officially recognized within a specific geographic region.
  • B. regionOfMajorLanguage
    Indicates the geographic region where a particular language is predominantly spoken or holds major usage.
  • C. languageArea
    Indicates the geographic or cultural region in which a particular language is used or predominantly spoken.
  • D. recognizedRegionalLanguage
    Indicates that a language holds officially recognized status within a specific region or subnational jurisdiction.
  • E. languageOfWorkOrName chosen
    Indicates the language in which a work is created or a name is expressed.
  • F. None of above.

Provenance (6 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_69a88b044ab48190add007487680f009 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abbf9e99f08190892d34485c8f2f25 completed March 7, 2026, 6:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5dbb6e8481908610337cfd2a4bd1 completed March 9, 2026, 5:42 a.m.
NEDg Description generation batch_69ae5e4a45a08190bd96af6cda06ab35 completed March 9, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ec4a35c8190bffc7a183497e764 completed March 9, 2026, 5:46 a.m.
PD Predicate disambiguation batch_69abbda706f4819094de73e1d1d1f539 completed March 7, 2026, 5:54 a.m.
Created at: March 4, 2026, 7:46 p.m.