Triple

T13038030
Position Surface form Disambiguated ID Type / Status
Subject Tom Güldemann E326613 entity
Predicate hasResearched P108399 FINISHED
Object Southern African linguistic area
The Southern African linguistic area is a region characterized by extensive language contact and shared structural features among diverse language families spoken in southern Africa.
E1018687 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: Southern African linguistic area | Statement: [Tom Güldemann, hasResearched, Southern African linguistic area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Southern African linguistic area
Context triple: [Tom Güldemann, hasResearched, Southern African linguistic area]
  • A. Central African linguistic area
    The Central African linguistic area is a region where diverse languages, including the Ubangian family, share convergent structural and phonological features due to long-term contact and diffusion.
  • B. Southern Bantu languages
    Southern Bantu languages are a major branch of the Bantu language family spoken primarily in southern Africa, including well-known languages such as Zulu, Xhosa, and Shona.
  • C. Bantu zone C
    Bantu zone C is a group of closely related Bantu languages within the Niger-Congo family, defined as one of the geographic-linguistic clusters in Malcolm Guthrie’s classification system.
  • D. Western Bantu languages
    Western Bantu languages are a major geographic and linguistic subgroup of the Bantu family spoken primarily in western Central Africa, including parts of countries such as Angola, Gabon, and the Republic of the Congo.
  • E. Bantu zone E
    Bantu zone E is a subgroup of Bantu languages in the Guthrie classification system, comprising closely related languages spoken primarily in parts of East and Central Africa.
  • 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: Southern African linguistic area
Triple: [Tom Güldemann, hasResearched, Southern African linguistic area]
Generated description
The Southern African linguistic area is a region characterized by extensive language contact and shared structural features among diverse language families spoken in southern Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Southern African linguistic area
Target entity description: The Southern African linguistic area is a region characterized by extensive language contact and shared structural features among diverse language families spoken in southern Africa.
  • A. Central African linguistic area
    The Central African linguistic area is a region where diverse languages, including the Ubangian family, share convergent structural and phonological features due to long-term contact and diffusion.
  • B. Southern Bantu languages
    Southern Bantu languages are a major branch of the Bantu language family spoken primarily in southern Africa, including well-known languages such as Zulu, Xhosa, and Shona.
  • C. Bantu zone C
    Bantu zone C is a group of closely related Bantu languages within the Niger-Congo family, defined as one of the geographic-linguistic clusters in Malcolm Guthrie’s classification system.
  • D. Western Bantu languages
    Western Bantu languages are a major geographic and linguistic subgroup of the Bantu family spoken primarily in western Central Africa, including parts of countries such as Angola, Gabon, and the Republic of the Congo.
  • E. Bantu zone E
    Bantu zone E is a subgroup of Bantu languages in the Guthrie classification system, comprising closely related languages spoken primarily in parts of East and Central Africa.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasResearched
Context triple: [Tom Güldemann, hasResearched, Southern African linguistic area]
  • A. hasResearchStatus
    Indicates that an entity holds a particular stage or condition within a research process, such as planned, in progress, completed, or published.
  • B. hasResearchFunction
    Indicates that an entity possesses a role, capacity, or function specifically related to conducting or supporting research activities.
  • C. hasResearchGoal
    Indicates that an entity has a specific research objective, aim, or target it is pursuing or designed to address.
  • D. hasResearcher
    Indicates that an entity is associated with or linked to a specific researcher responsible for work, study, or investigation related to it.
  • E. hasResearchFinding
    Indicates that an entity has produced, contains, or is associated with a specific research finding or result.
  • F. None of above. chosen

Provenance (7 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d98a9829b48190b23624b6b3df4600 completed April 10, 2026, 11:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbd12eec81908ad5dae638c2210e completed May 3, 2026, 4:15 a.m.
NEDg Description generation batch_69f6cdc285788190a05a51295306f087 completed May 3, 2026, 4:23 a.m.
NED2 Entity disambiguation (via description) batch_69f6ceafcca88190bcd65be3c4440987 completed May 3, 2026, 4:27 a.m.
PD Predicate disambiguation batch_69d9803aca4c8190b1015cd159cc47a9 completed April 10, 2026, 10:56 p.m.
PDg Predicate description generation batch_69d98a9577d081908ddef9ea77e408e2 completed April 10, 2026, 11:41 p.m.
Created at: April 9, 2026, 8:55 p.m.