Triple

T9480353
Position Surface form Disambiguated ID Type / Status
Subject Piedmont E228618 entity
Predicate hasTraditionalCheese P19484 FINISHED
Object Toma
Toma is a traditional semi-hard cow’s milk cheese from Italy’s Piedmont region, known for its mild, buttery flavor and smooth, elastic texture.
 E802468 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: Toma | Statement: [Piedmont, hasTraditionalCheese, Toma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Toma
Context triple: [Piedmont, hasTraditionalCheese, Toma]
  • A. Toma
    Toma is a major Mande language spoken primarily in Guinea and neighboring West African countries.
  • B. Tanto
    Tanto was a former town in Hyōgo Prefecture, Japan, that later became part of the expanded city of Toyooka through municipal merger.
  • C. Toda
    Toda is a Southern Dravidian language spoken by the Toda people of the Nilgiri Hills in southern India, known for its highly complex phonology and small speaker population.
  • D. Toda
    Toda is a subgroup of the Seediq, an Indigenous people of Taiwan known for their distinct language and cultural traditions.
  • E. Tarouca
    Tarouca is a municipality in Portugal’s Douro region, known for its historic monasteries, vineyards, and scenic river valley 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: Toma
Triple: [Piedmont, hasTraditionalCheese, Toma]
Generated description
Toma is a traditional semi-hard cow’s milk cheese from Italy’s Piedmont region, known for its mild, buttery flavor and smooth, elastic texture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Toma
Target entity description: Toma is a traditional semi-hard cow’s milk cheese from Italy’s Piedmont region, known for its mild, buttery flavor and smooth, elastic texture.
  • A. Toma
    Toma is a major Mande language spoken primarily in Guinea and neighboring West African countries.
  • B. Tanto
    Tanto was a former town in Hyōgo Prefecture, Japan, that later became part of the expanded city of Toyooka through municipal merger.
  • C. Toda
    Toda is a Southern Dravidian language spoken by the Toda people of the Nilgiri Hills in southern India, known for its highly complex phonology and small speaker population.
  • D. Toda
    Toda is a subgroup of the Seediq, an Indigenous people of Taiwan known for their distinct language and cultural traditions.
  • E. Tarouca
    Tarouca is a municipality in Portugal’s Douro region, known for its historic monasteries, vineyards, and scenic river valley 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_69ca84730a5081908de282651019bf2f completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd8016813881908dafc026779c89c4 completed April 1, 2026, 8:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69d12cf7526c8190b96693bdc13743d5 completed April 4, 2026, 3:23 p.m.
NEDg Description generation batch_69d12ed9240c8190bd206a0d2263e249 completed April 4, 2026, 3:31 p.m.
NED2 Entity disambiguation (via description) batch_69d12f870d2881909b0b50adfd2ba13b completed April 4, 2026, 3:34 p.m.
Created at: March 30, 2026, 7:54 p.m.