Triple

T370909
Position Surface form Disambiguated ID Type / Status
Subject Joseph Pulitzer E8265 entity
Predicate spouse P13 FINISHED
Object Kate Davis
Kate Davis was the wife of influential newspaper publisher and journalist Joseph Pulitzer.
E164901 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: Kate Davis | Statement: [Joseph Pulitzer, spouse, Kate Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Davis
Context triple: [Joseph Pulitzer, spouse, Kate Davis]
  • A. Lyn Davis
    Lyn Davis is best known as the wife of influential American television writer and producer Norman Lear.
  • B. Emily Carmichael
    Emily Carmichael is an American filmmaker and screenwriter known for her work on genre films such as Pacific Rim: Uprising and for her distinctive, imaginative storytelling style.
  • C. Katherine Hudson
    Katherine Hudson was the wife of English explorer Henry Hudson, known primarily through historical records of his voyages and family.
  • D. Mary Newman
    Mary Newman was the first wife of the English sea captain and explorer Sir Francis Drake in the late 16th century.
  • E. Mary Grace Slattery
    Mary Grace Slattery was the first wife of American playwright Arthur Miller, whom he married before achieving his major theatrical success.
  • 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: Kate Davis
Triple: [Joseph Pulitzer, spouse, Kate Davis]
Generated description
Kate Davis was the wife of influential newspaper publisher and journalist Joseph Pulitzer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kate Davis
Target entity description: Kate Davis was the wife of influential newspaper publisher and journalist Joseph Pulitzer.
  • A. Lyn Davis
    Lyn Davis is best known as the wife of influential American television writer and producer Norman Lear.
  • B. Emily Carmichael
    Emily Carmichael is an American filmmaker and screenwriter known for her work on genre films such as Pacific Rim: Uprising and for her distinctive, imaginative storytelling style.
  • C. Katherine Hudson
    Katherine Hudson was the wife of English explorer Henry Hudson, known primarily through historical records of his voyages and family.
  • D. Mary Newman
    Mary Newman was the first wife of the English sea captain and explorer Sir Francis Drake in the late 16th century.
  • E. Mary Grace Slattery
    Mary Grace Slattery was the first wife of American playwright Arthur Miller, whom he married before achieving his major theatrical success.
  • 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_69a2e7f2ec648190b42bc7db424f8109 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ebff472881909fad81d597425ea6 completed Feb. 28, 2026, 1:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad089201a08190a84c7d8f32238297 completed March 8, 2026, 5:26 a.m.
NEDg Description generation batch_69ad09206e988190ad76f8beaa8f9fe6 completed March 8, 2026, 5:29 a.m.
NED2 Entity disambiguation (via description) batch_69ad0a30bcdc81908090d6a094ece0f4 completed March 8, 2026, 5:33 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.