Triple

T3873774
Position Surface form Disambiguated ID Type / Status
Subject Minervois AOC E92447 entity
Predicate grapeVarietyUsed P975 FINISHED
Object Piquepoul Noir
Piquepoul Noir is a rare, traditional red wine grape variety from southern France, known for producing light, fresh, and aromatic wines often used in blends.
E395512 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: Piquepoul Noir | Statement: [Minervois AOC, grapeVarietyUsed, Piquepoul Noir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Piquepoul Noir
Context triple: [Minervois AOC, grapeVarietyUsed, Piquepoul Noir]
  • A. Limousin
    Limousin is a former administrative region in central France known for its rural landscapes, cattle breeding, and historic towns such as Limoges and Tulle.
  • B. Mouton-Duvernet
    Mouton-Duvernet is a Paris Métro station in the 14th arrondissement, serving the Montparnasse area and named after the French general Régis Barthélemy Mouton-Duvernet.
  • C. Marans
    Marans is a French chicken breed renowned for its dark chocolate-brown eggs and dual-purpose use for both meat and egg production.
  • D. Mouton
    Mouton is an academic publishing house known for its influential works in linguistics and related fields.
  • E. Rosier
    Rosier is a surname of French origin borne by various notable individuals across different fields.
  • 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: Piquepoul Noir
Triple: [Minervois AOC, grapeVarietyUsed, Piquepoul Noir]
Generated description
Piquepoul Noir is a rare, traditional red wine grape variety from southern France, known for producing light, fresh, and aromatic wines often used in blends.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Piquepoul Noir
Target entity description: Piquepoul Noir is a rare, traditional red wine grape variety from southern France, known for producing light, fresh, and aromatic wines often used in blends.
  • A. Limousin
    Limousin is a former administrative region in central France known for its rural landscapes, cattle breeding, and historic towns such as Limoges and Tulle.
  • B. Mouton-Duvernet
    Mouton-Duvernet is a Paris Métro station in the 14th arrondissement, serving the Montparnasse area and named after the French general Régis Barthélemy Mouton-Duvernet.
  • C. Marans
    Marans is a French chicken breed renowned for its dark chocolate-brown eggs and dual-purpose use for both meat and egg production.
  • D. Mouton
    Mouton is an academic publishing house known for its influential works in linguistics and related fields.
  • E. Rosier
    Rosier is a surname of French origin borne by various notable individuals across different fields.
  • 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_69aed967448c819086c4b358d37b25aa completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec581adc81909219e6f025fc97c2 completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5124cdf588190b3b83ee8fb29450a completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b5132715888190bc5ba6182965e813 completed March 14, 2026, 7:49 a.m.
NED2 Entity disambiguation (via description) batch_69b513b11dcc8190a2c2e3f27b4cf25e completed March 14, 2026, 7:52 a.m.
Created at: March 9, 2026, 3:20 p.m.