Triple

T12167043
Position Surface form Disambiguated ID Type / Status
Subject Terri Windling E289859 entity
Predicate coEditorWith P8375 FINISHED
Object Ellen Datlow
Ellen Datlow is an acclaimed American editor best known for her influential work in horror, fantasy, and science fiction anthologies.
E966672 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: Ellen Datlow | Statement: [Terri Windling, coEditorWith, Ellen Datlow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellen Datlow
Context triple: [Terri Windling, coEditorWith, Ellen Datlow]
  • A. Ellen Bowen
    Ellen Bowen is a fictional character from the 1951 MGM musical film "Royal Wedding," which starred Fred Astaire.
  • B. Ellen Bowen
    Ellen Bowen is a woman known primarily as the sister of Tom Bowen, the Australian manual therapist who founded the Bowen technique.
  • C. Ellen Thomas
    Ellen Thomas is a British actress known for her work in television, film, and theatre, including prominent roles in UK dramas and comedies.
  • D. Lenore Kipp
    Lenore Kipp was the wife of American actor Joseph Cotten, known primarily for her long marriage to the classic Hollywood star.
  • E. Maria Ewing
    Maria Ewing was an acclaimed American opera singer and actress known for her intense dramatic presence and versatile mezzo-soprano and soprano roles on major international stages.
  • 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: Ellen Datlow
Triple: [Terri Windling, coEditorWith, Ellen Datlow]
Generated description
Ellen Datlow is an acclaimed American editor best known for her influential work in horror, fantasy, and science fiction anthologies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ellen Datlow
Target entity description: Ellen Datlow is an acclaimed American editor best known for her influential work in horror, fantasy, and science fiction anthologies.
  • A. Ellen Bowen
    Ellen Bowen is a fictional character from the 1951 MGM musical film "Royal Wedding," which starred Fred Astaire.
  • B. Ellen Bowen
    Ellen Bowen is a woman known primarily as the sister of Tom Bowen, the Australian manual therapist who founded the Bowen technique.
  • C. Ellen Thomas
    Ellen Thomas is a British actress known for her work in television, film, and theatre, including prominent roles in UK dramas and comedies.
  • D. Lenore Kipp
    Lenore Kipp was the wife of American actor Joseph Cotten, known primarily for her long marriage to the classic Hollywood star.
  • E. Maria Ewing
    Maria Ewing was an acclaimed American opera singer and actress known for her intense dramatic presence and versatile mezzo-soprano and soprano roles on major international stages.
  • 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_69d6ab4d6c00819095a9a7c35de83cfb completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915d85c088190a74fb7590877659b completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f6a2716081909620a9d11cfcc2d8 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f6018043f48190a3062de4e0d4a3f5 completed May 2, 2026, 1:52 p.m.
NED2 Entity disambiguation (via description) batch_69f60232d89881909f254da6deb7f321 completed May 2, 2026, 1:54 p.m.
Created at: April 8, 2026, 9:50 p.m.