Triple

T23477002
Position Surface form Disambiguated ID Type / Status
Subject Duke of la Unión E570290 entity
Predicate styleOfAddress P536 FINISHED
Object Duke
A duke is a high-ranking noble title traditionally positioned just below a monarch in many European aristocratic hierarchies.
E30157 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: Duke | Statement: [Duke of la Unión, styleOfAddress, Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke
Context triple: [Duke of la Unión, styleOfAddress, Duke]
  • A. Duke
    Duke was a privateering ship commanded by English sea captain and privateer Woodes Rogers during his early 18th-century voyages.
  • B. Duke
    Duke is the men's basketball team of Duke University, renowned as one of the most successful and storied programs in NCAA history.
  • C. Duke
    Duke is a prominent clan of the Efik people, historically influential in their social and political organization in southeastern Nigeria.
  • D. Duke
    Duke is the bulldog mascot representing York Community High School’s athletic teams and school spirit.
  • E. Duke
    Duke is a narrow-gauge steam locomotive character from the Skarloey Railway in The Railway Series and Thomas & Friends franchise, known for his old-fashioned, strict yet caring personality.
  • 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: Duke
Triple: [Duke of la Unión, styleOfAddress, Duke]
Generated description
A duke is a high-ranking noble title traditionally positioned just below a monarch in many European aristocratic hierarchies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Duke
Target entity description: A duke is a high-ranking noble title traditionally positioned just below a monarch in many European aristocratic hierarchies.
  • A. Duke chosen
    A duke is the highest hereditary noble title in the British peerage system below the monarch, historically associated with great landholdings and significant political influence.
  • B. Duke
    Duke is an English surname historically associated with nobility and high social rank.
  • C. Duke
    Duke is a masculine given name and nickname, often used in English-speaking countries and associated with a sense of nobility or high status.
  • D. Duke
    Duke is a fictional nobleman in Miguel de Cervantes’ "Don Quixote" who, along with a duchess, orchestrates elaborate pranks on Don Quixote and Sancho Panza, including Sancho’s mock governorship of the Ínsula Barataria.
  • E. Duke
    Duke is a prominent American family name most famously associated with the wealthy industrialist and philanthropic Duke family of North Carolina.
  • F. None of above.

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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a74dbea8819085ca84391039e7f7 completed April 29, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c82622f08819087b983bfd69efe5d completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6f06a348190bfdba0452077f45b completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca7bdf7f08190b50191b029480fc5 completed May 19, 2026, 6:11 p.m.
Created at: April 17, 2026, 6:01 p.m.