Triple

T6977702
Position Surface form Disambiguated ID Type / Status
Subject Mary of Burgundy, Duchess of Savoy E161754 entity
Predicate residence P75 FINISHED
Object Burgundy E6890 NE FINISHED

How this triple was built (2 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: Burgundy | Statement: [Mary of Burgundy, Duchess of Savoy, residence, Burgundy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burgundy
Context triple: [Mary of Burgundy, Duchess of Savoy, residence, Burgundy]
  • A. Burgundy chosen
    Burgundy is a renowned wine-producing region in eastern France, famous for its high-quality Chardonnay and Pinot Noir wines.
  • B. Burgundy
    Burgundy is a mid-level membership tier in the Privilege Club loyalty program, offering enhanced benefits and rewards to frequent participants.
  • C. Beaujolais
    Beaujolais is a French wine-producing region best known for its light, fruity red wines made primarily from the Gamay grape, including the popular Beaujolais Nouveau.
  • D. Mâconnais
    Mâconnais is a wine-producing subregion in southern Burgundy, France, best known for its Chardonnay-based white wines.
  • E. Côte Chalonnaise
    Côte Chalonnaise is a wine-producing subregion of Burgundy in eastern France, known for its value-driven red and white wines primarily from Pinot Noir and Chardonnay.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c68854a0d88190bc0bf82263f1afce completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db68d25c8190a1776908619ad979 completed March 27, 2026, 7:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a0ad57c81909aec9f619dc68bd7 completed March 28, 2026, 5:41 a.m.
Created at: March 27, 2026, 2:31 p.m.