Triple

T23289010
Position Surface form Disambiguated ID Type / Status
Subject House of Ji E589974 entity
Predicate nobleTitle P914 FINISHED
Object Duke of Lu NE NERFINISHED

How this triple was built (3 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: Duke of Lu | Statement: [House of Ji, nobleTitle, Duke of Lu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke of Lu
Context triple: [House of Ji, nobleTitle, Duke of Lu]
  • A. Duke of Bar
    The Duke of Bar was a hereditary title in the French nobility associated with the rulers of the Duchy of Bar in northeastern France, often held by members of the House of Lorraine.
  • B. Duke of Berg
    The Duke of Berg was the title held by the sovereign ruler of the historic Duchy of Berg in the Holy Roman Empire, located in what is now western Germany.
  • C. Duke of Limburg
    The Duke of Limburg was a noble title historically associated with the ruler of the Duchy of Limburg in the Low Countries, later held ceremonially by Dutch monarchs such as William I of the Netherlands.
  • D. Duke of Neiva
    The Duke of Neiva was a Portuguese noble title historically associated with the royal heir Miguel da Paz, Prince of Portugal.
  • E. Duke of Lauenburg
    The Duke of Lauenburg was a noble title in the Kingdom of Prussia, notably granted to the influential 19th-century statesman Otto von Bismarck in recognition of his role in German unification.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Duke of Lu
Target entity description: The Duke of Lu was a hereditary noble title in ancient China associated with the ruling lineage of the State of Lu, traditionally linked to the Zhou royal clan.
  • A. Duke of Bar
    The Duke of Bar was a hereditary title in the French nobility associated with the rulers of the Duchy of Bar in northeastern France, often held by members of the House of Lorraine.
  • B. Duke of Berg
    The Duke of Berg was the title held by the sovereign ruler of the historic Duchy of Berg in the Holy Roman Empire, located in what is now western Germany.
  • C. Duke of Limburg
    The Duke of Limburg was a noble title historically associated with the ruler of the Duchy of Limburg in the Low Countries, later held ceremonially by Dutch monarchs such as William I of the Netherlands.
  • D. Duke of Neiva
    The Duke of Neiva was a Portuguese noble title historically associated with the royal heir Miguel da Paz, Prince of Portugal.
  • E. Duke of Lauenburg
    The Duke of Lauenburg was a noble title in the Kingdom of Prussia, notably granted to the influential 19th-century statesman Otto von Bismarck in recognition of his role in German unification.
  • F. None of above. chosen

Provenance (2 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_69e25d1af9d88190a0b9b5e8fa608618 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19649570c8190b565fafa55b1f886 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 5:01 p.m.