Triple

T22809026
Position Surface form Disambiguated ID Type / Status
Subject Peter Dickinson E564620 entity
Predicate spouse P13 FINISHED
Object Robin McKinley
Robin McKinley is an American fantasy author best known for her richly imagined retellings of classic fairy tales, including "Beauty" and "Spindle's End."
E1554902 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: Robin McKinley | Statement: [Peter Dickinson, spouse, Robin McKinley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robin McKinley
Context triple: [Peter Dickinson, spouse, Robin McKinley]
  • A. Pauline Baynes
    Pauline Baynes was a British illustrator best known for her iconic artwork for J.R.R. Tolkien’s Middle-earth writings and C.S. Lewis’s The Chronicles of Narnia.
  • B. Terri Windling
    Terri Windling is an American editor, author, and artist renowned for her influential work in fantasy literature and mythic arts.
  • C. Gail Carson Levine
    Gail Carson Levine is an American author best known for her Newbery Honor–winning children's fantasy novel "Ella Enchanted."
  • D. Julie Brett
    Julie Brett is the mother of British television producer and talent show judge Simon Cowell.
  • E. Jessica Burdett
    Jessica Burdett is a television producer best known for her executive production work on the psychological thriller series "Behind Her Eyes."
  • 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: Robin McKinley
Triple: [Peter Dickinson, spouse, Robin McKinley]
Generated description
Robin McKinley is an American fantasy author best known for her richly imagined retellings of classic fairy tales, including "Beauty" and "Spindle's End."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robin McKinley
Target entity description: Robin McKinley is an American fantasy author best known for her richly imagined retellings of classic fairy tales, including "Beauty" and "Spindle's End."
  • A. Pauline Baynes
    Pauline Baynes was a British illustrator best known for her iconic artwork for J.R.R. Tolkien’s Middle-earth writings and C.S. Lewis’s The Chronicles of Narnia.
  • B. Terri Windling
    Terri Windling is an American editor, author, and artist renowned for her influential work in fantasy literature and mythic arts.
  • C. Gail Carson Levine
    Gail Carson Levine is an American author best known for her Newbery Honor–winning children's fantasy novel "Ella Enchanted."
  • D. Julie Brett
    Julie Brett is the mother of British television producer and talent show judge Simon Cowell.
  • E. Jessica Burdett
    Jessica Burdett is a television producer best known for her executive production work on the psychological thriller series "Behind Her Eyes."
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17d5e0b088190ad0b9cc0d5aa1d96 completed April 29, 2026, 3:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b9e9fb140819093b5c1e0b9511386 completed May 18, 2026, 11:19 p.m.
NEDg Description generation batch_6a0b9fac99ac8190aadb79f1d5a2d65f completed May 18, 2026, 11:24 p.m.
NED2 Entity disambiguation (via description) batch_6a0ba07b3cb481908f1e47a3a1f3a139 completed May 18, 2026, 11:27 p.m.
Created at: April 17, 2026, 3:32 p.m.