Triple

T12653974
Position Surface form Disambiguated ID Type / Status
Subject Loko E302234 entity
Predicate hasAlternativeName P39 FINISHED
Object Loko language
Loko language is a Southern Atlantic language spoken primarily by the Loko people in Sierra Leone.
 E996638 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: Loko language | Statement: [Loko, hasAlternativeName, Loko language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Loko language
Context triple: [Loko, hasAlternativeName, Loko language]
  • A. Lokoya language
    The Lokoya language is a Nilo-Saharan language spoken by the Lokoya people of South Sudan.
  • B. Lotuko language
    The Lotuko language is an Eastern Nilotic language spoken primarily by the Lotuko people of South Sudan.
  • C. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • D. Luvale language
    The Luvale language is a Bantu language spoken primarily by the Luvale people of northwestern Zambia and eastern Angola.
  • E. Lozi language
    The Lozi language is a Bantu language spoken primarily in western Zambia and surrounding regions, serving as the main language of the Lozi people and a lingua franca in parts of south-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: Loko language
Triple: [Loko, hasAlternativeName, Loko language]
Generated description
Loko language is a Southern Atlantic language spoken primarily by the Loko people in Sierra Leone.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Loko language
Target entity description: Loko language is a Southern Atlantic language spoken primarily by the Loko people in Sierra Leone.
  • A. Lokoya language
    The Lokoya language is a Nilo-Saharan language spoken by the Lokoya people of South Sudan.
  • B. Lotuko language
    The Lotuko language is an Eastern Nilotic language spoken primarily by the Lotuko people of South Sudan.
  • C. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • D. Luvale language
    The Luvale language is a Bantu language spoken primarily by the Luvale people of northwestern Zambia and eastern Angola.
  • E. Lozi language
    The Lozi language is a Bantu language spoken primarily in western Zambia and surrounding regions, serving as the main language of the Lozi people and a lingua franca in parts of south-central Africa.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96160730c81909e1aa3efb51bf159 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6688104d48190939933b93b7e60cc completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f66c572f848190a8cad6311d3315a3 completed May 2, 2026, 9:27 p.m.
NED2 Entity disambiguation (via description) batch_69f66cef79148190a052fb9ade3b0d27 completed May 2, 2026, 9:30 p.m.
Created at: April 9, 2026, 5:18 p.m.