Triple

T14568657
Position Surface form Disambiguated ID Type / Status
Subject Maisie Williams E341853 entity
Predicate founded P104 FINISHED
Object Daisie
Daisie is a creative networking and collaboration platform co-founded by actress Maisie Williams to help emerging artists showcase their work and connect with opportunities.
 E1106856 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: Daisie | Statement: [Maisie Williams, founded, Daisie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Daisie
Context triple: [Maisie Williams, founded, Daisie]
  • A. Daisy Jane
    "Daisy Jane" is a soft rock ballad by the band America, known for its gentle melody and introspective lyrics.
  • B. Tillie
    Tillie is a character in the 1967 film "Guess Who's Coming to Dinner," serving as the Drayton family's outspoken and protective housekeeper.
  • C. Elsie
    Elsie is a fictional character from the post-apocalyptic virtual reality game "After the Fall."
  • D. Elsie
    Elsie is the internal codename Apple used for the Macintosh LC personal computer during its development.
  • E. Elsie
    Elsie is a feminine given name, originally a diminutive of Elizabeth, that has become a standalone name in its own right.
  • 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: Daisie
Triple: [Maisie Williams, founded, Daisie]
Generated description
Daisie is a creative networking and collaboration platform co-founded by actress Maisie Williams to help emerging artists showcase their work and connect with opportunities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Daisie
Target entity description: Daisie is a creative networking and collaboration platform co-founded by actress Maisie Williams to help emerging artists showcase their work and connect with opportunities.
  • A. Daisy Jane
    "Daisy Jane" is a soft rock ballad by the band America, known for its gentle melody and introspective lyrics.
  • B. Tillie
    Tillie is a character in the 1967 film "Guess Who's Coming to Dinner," serving as the Drayton family's outspoken and protective housekeeper.
  • C. Elsie
    Elsie is a fictional character from the post-apocalyptic virtual reality game "After the Fall."
  • D. Elsie
    Elsie is the internal codename Apple used for the Macintosh LC personal computer during its development.
  • E. Elsie
    Elsie is a feminine given name, originally a diminutive of Elizabeth, that has become a standalone name in its own right.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb38d89fc819086709fd3607b835f completed April 14, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ac858108190b7c90130f18b0ddb completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c3678048190a23b509e963c1ade completed May 8, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_69fd8d609684819090a9c3f2304f4a6a completed May 8, 2026, 7:14 a.m.
Created at: April 10, 2026, 1:23 a.m.