Triple

T21091033
Position Surface form Disambiguated ID Type / Status
Subject Felicity d'Abreu Crosland E519636 entity
Predicate hasNickname P39 FINISHED
Object Liccy
Liccy is the nickname of Felicity d'Abreu Crosland, the widow of author Roald Dahl and a film producer.
 E1466298 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: Liccy | Statement: [Felicity d'Abreu Crosland, hasNickname, Liccy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Liccy
Context triple: [Felicity d'Abreu Crosland, hasNickname, Liccy]
  • A. Lolli
    Lolli is a bitcoin and cashback rewards platform that lets users earn cryptocurrency when they shop online and in-store at partner retailers.
  • B. Lick
    "Lick" is a dancehall- and hip hop-influenced single by Jamaican artist Shenseea featuring Megan Thee Stallion, known for its sexually explicit lyrics and viral choreography.
  • C. Lick
    Lick is the nickname of Joseph Carl Robnett Licklider, a pioneering American computer scientist whose ideas helped lay the foundations for interactive computing and the internet.
  • D. Cicia
    Cicia is a small inhabited island in Fiji’s Lau archipelago, known for its traditional village life and remote South Pacific setting.
  • E. Dilly
    Dilly is the nickname of British classicist and World War II codebreaker Alfred Dillwyn "Dilly" Knox, known for his work at Bletchley Park.
  • 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: Liccy
Triple: [Felicity d'Abreu Crosland, hasNickname, Liccy]
Generated description
Liccy is the nickname of Felicity d'Abreu Crosland, the widow of author Roald Dahl and a film producer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Liccy
Target entity description: Liccy is the nickname of Felicity d'Abreu Crosland, the widow of author Roald Dahl and a film producer.
  • A. Lolli
    Lolli is a bitcoin and cashback rewards platform that lets users earn cryptocurrency when they shop online and in-store at partner retailers.
  • B. Lick
    "Lick" is a dancehall- and hip hop-influenced single by Jamaican artist Shenseea featuring Megan Thee Stallion, known for its sexually explicit lyrics and viral choreography.
  • C. Lick
    Lick is the nickname of Joseph Carl Robnett Licklider, a pioneering American computer scientist whose ideas helped lay the foundations for interactive computing and the internet.
  • D. Cicia
    Cicia is a small inhabited island in Fiji’s Lau archipelago, known for its traditional village life and remote South Pacific setting.
  • E. Dilly
    Dilly is the nickname of British classicist and World War II codebreaker Alfred Dillwyn "Dilly" Knox, known for his work at Bletchley Park.
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094ea7f881909db83bf6961b41ec completed April 21, 2026, 5:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a095a5a70c88190812a7ec9efa8fa42 completed May 17, 2026, 6:04 a.m.
NEDg Description generation batch_6a095c017bec81909fd6c73a0fb677df completed May 17, 2026, 6:11 a.m.
NED2 Entity disambiguation (via description) batch_6a095cee4c308190a08844f285231ff9 completed May 17, 2026, 6:15 a.m.
Created at: April 16, 2026, 2:51 p.m.