Triple

T2669556
Position Surface form Disambiguated ID Type / Status
Subject Wace E55716 entity
Predicate notableWork P4 FINISHED
Object Roman de Rou E288138 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: Roman de Rou | Statement: [Wace, notableWork, Roman de Rou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman de Rou
Context triple: [Wace, notableWork, Roman de Rou]
  • A. Roman de Rou chosen
    Roman de Rou is a 12th-century Norman-French verse chronicle by Wace that recounts the history and deeds of the dukes of Normandy, including William the Conqueror.
  • B. King of Burgundy
    The King of Burgundy was the medieval monarch who ruled the historical Kingdom of Burgundy in Western Europe, a realm that later came under the control of the Salian dynasty of the Holy Roman Empire.
  • C. Lady of Montargis
    Lady of Montargis is a noble title historically associated with Eleanor of England, Countess of Pembroke, reflecting her lordship over the French lordship of Montargis.
  • D. Amadis
    Amadis is a French Baroque opera by Jean-Baptiste Lully, based on the chivalric romance "Amadis de Gaula" and known for its blend of heroic drama and elaborate musical spectacle.
  • E. Lord of Montpellier
    Lord of Montpellier was a medieval feudal title associated with the rule of the important commercial and cultural city of Montpellier in southern France.
  • 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_69ab49e54de48190be708cd1cf8be073 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd98d32ac8190b8edd9421b706532 completed March 7, 2026, 7:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69afaf5115648190bf1c66882410642d completed March 10, 2026, 5:42 a.m.
Created at: March 6, 2026, 9:54 p.m.