Triple

T348030
Position Surface form Disambiguated ID Type / Status
Subject Bordeaux E6982 entity
Predicate hasSubregion P285 FINISHED
Object Fronsac
Fronsac is a French wine appellation on the right bank of the Dordogne River, known for its Merlot-based red wines and proximity to Bordeaux.
E51137 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: Fronsac | Statement: [Bordeaux, hasSubregion, Fronsac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fronsac
Context triple: [Bordeaux, hasSubregion, Fronsac]
  • A. Châteauroux
    Châteauroux is a city in central France that will host the shooting events for the 2024 Summer Olympics.
  • B. Bordeaux
    Bordeaux is a renowned wine-producing region in southwestern France, famous for its prestigious red blends and long winemaking tradition.
  • C. Saint-Émilion
    Saint-Émilion is a renowned wine-producing appellation and medieval village on Bordeaux’s Right Bank, famous for its Merlot-dominant red wines and UNESCO-listed historic vineyards.
  • D. Médoc
    Médoc is a renowned wine-producing area in southwestern France, famous for its high-quality red Bordeaux wines made predominantly from Cabernet Sauvignon.
  • E. Pessac-Léognan
    Pessac-Léognan is a prestigious wine appellation in southwestern France known for its high-quality red and dry white wines, including several classified growths.
  • 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: Fronsac
Triple: [Bordeaux, hasSubregion, Fronsac]
Generated description
Fronsac is a French wine appellation on the right bank of the Dordogne River, known for its Merlot-based red wines and proximity to Bordeaux.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fronsac
Target entity description: Fronsac is a French wine appellation on the right bank of the Dordogne River, known for its Merlot-based red wines and proximity to Bordeaux.
  • A. Châteauroux
    Châteauroux is a city in central France that will host the shooting events for the 2024 Summer Olympics.
  • B. Bordeaux
    Bordeaux is a renowned wine-producing region in southwestern France, famous for its prestigious red blends and long winemaking tradition.
  • C. Saint-Émilion
    Saint-Émilion is a renowned wine-producing appellation and medieval village on Bordeaux’s Right Bank, famous for its Merlot-dominant red wines and UNESCO-listed historic vineyards.
  • D. Médoc
    Médoc is a renowned wine-producing area in southwestern France, famous for its high-quality red Bordeaux wines made predominantly from Cabernet Sauvignon.
  • E. Pessac-Léognan
    Pessac-Léognan is a prestigious wine appellation in southwestern France known for its high-quality red and dry white wines, including several classified growths.
  • 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_69a2e7951ba08190960e90823b5078f3 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2eb1c1c908190b3a01de893207ed1 completed Feb. 28, 2026, 1:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a413ee31fc81908cbda4c0737d1b33 completed March 1, 2026, 10:24 a.m.
NEDg Description generation batch_69a414552e488190b02254f5c078eeb1 completed March 1, 2026, 10:26 a.m.
NED2 Entity disambiguation (via description) batch_69a41485f4048190b47a78d05fa775b1 completed March 1, 2026, 10:27 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.