Triple

T6828208
Position Surface form Disambiguated ID Type / Status
Subject Paul Auster E157067 entity
Predicate spouse P13 FINISHED
Object Lydia Davis
Lydia Davis is an American writer renowned for her extremely short, experimental short stories and her acclaimed translations of French literature.
 E622136 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: Lydia Davis | Statement: [Paul Auster, spouse, Lydia Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lydia Davis
Context triple: [Paul Auster, spouse, Lydia Davis]
  • A. Anne Hartnett
    Anne Hartnett is an individual notable enough to be recognized as a prominent bearer of the surname Hartnett.
  • B. Jorie Graham
    Jorie Graham is a Pulitzer Prize–winning American poet renowned for her intellectually rigorous, formally innovative work that explores history, perception, and the natural world.
  • C. C. D. Wright
    C. D. Wright was an American poet known for her innovative, genre-blurring work that often explored place, justice, and the voices of marginalized communities.
  • D. Doug Mahon
    Doug Mahon is a technology entrepreneur best known as a founder of the data storage company Seagate Technology.
  • E. Lydia West
    Lydia West is a British actress best known for her acclaimed role in the television drama series "It's a Sin."
  • 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: Lydia Davis
Triple: [Paul Auster, spouse, Lydia Davis]
Generated description
Lydia Davis is an American writer renowned for her extremely short, experimental short stories and her acclaimed translations of French literature.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lydia Davis
Target entity description: Lydia Davis is an American writer renowned for her extremely short, experimental short stories and her acclaimed translations of French literature.
  • A. Anne Hartnett
    Anne Hartnett is an individual notable enough to be recognized as a prominent bearer of the surname Hartnett.
  • B. Jorie Graham
    Jorie Graham is a Pulitzer Prize–winning American poet renowned for her intellectually rigorous, formally innovative work that explores history, perception, and the natural world.
  • C. C. D. Wright
    C. D. Wright was an American poet known for her innovative, genre-blurring work that often explored place, justice, and the voices of marginalized communities.
  • D. Doug Mahon
    Doug Mahon is a technology entrepreneur best known as a founder of the data storage company Seagate Technology.
  • E. Lydia West
    Lydia West is a British actress best known for her acclaimed role in the television drama series "It's a Sin."
  • 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_69c6882a5b5c8190917a7db9ed36bad1 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d6254bd88190a2a424537c2c12e2 completed March 27, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723f49bdc8190af39b34dbaf3f0c9 completed March 28, 2026, 12:42 a.m.
NEDg Description generation batch_69c724d7f0308190abb494ea663ceeb9 completed March 28, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69c72568866c8190bf88a02e566d5c3a completed March 28, 2026, 12:48 a.m.
Created at: March 27, 2026, 2:18 p.m.