Triple

T721070
Position Surface form Disambiguated ID Type / Status
Subject Occitan E14615 entity
Predicate hasEndonym P1435 FINISHED
Object lenga d'òc
lenga d'òc is the native Occitan name for the Romance language historically spoken across southern France and parts of Italy and Spain.
E86999 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: lenga d'òc | Statement: [Occitan, hasEndonym, lenga d'òc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: lenga d'òc
Context triple: [Occitan, hasEndonym, lenga d'òc]
  • A. Dili
    Dili is the coastal capital and largest city of Timor-Leste, serving as its political, economic, and cultural center.
  • B. Langues
    Langues were the regional administrative divisions of the Knights Hospitaller, grouping members by their geographic and linguistic origins.
  • C. Ladin language
    Ladin language is a Rhaeto-Romance language spoken primarily in the Dolomite mountain region of northern Italy.
  • D. Jèrriais
    Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
  • E. Sentinelese language
    The Sentinelese language is the undocumented and unclassified tongue spoken by the isolated Sentinelese people of North Sentinel Island in the Andaman archipelago.
  • 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: lenga d'òc
Triple: [Occitan, hasEndonym, lenga d'òc]
Generated description
lenga d'òc is the native Occitan name for the Romance language historically spoken across southern France and parts of Italy and Spain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: lenga d'òc
Target entity description: lenga d'òc is the native Occitan name for the Romance language historically spoken across southern France and parts of Italy and Spain.
  • A. Dili
    Dili is the coastal capital and largest city of Timor-Leste, serving as its political, economic, and cultural center.
  • B. Langues
    Langues were the regional administrative divisions of the Knights Hospitaller, grouping members by their geographic and linguistic origins.
  • C. Ladin language
    Ladin language is a Rhaeto-Romance language spoken primarily in the Dolomite mountain region of northern Italy.
  • D. Jèrriais
    Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
  • E. Sentinelese language
    The Sentinelese language is the undocumented and unclassified tongue spoken by the isolated Sentinelese people of North Sentinel Island in the Andaman archipelago.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a58fa41c819082de2cc4e0cb2943 completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a63759d6108190adcdeac45e4c7766 completed March 3, 2026, 1:20 a.m.
NEDg Description generation batch_69a63b158dc881909da0b90f498e9a43 completed March 3, 2026, 1:36 a.m.
NED2 Entity disambiguation (via description) batch_69a63eccc5a08190b39b7818dc61591c completed March 3, 2026, 1:52 a.m.
Created at: March 1, 2026, 7:37 p.m.