Triple

T1669570
Position Surface form Disambiguated ID Type / Status
Subject Sylvia Ashley E36092 entity
Predicate familyName P18 FINISHED
Object Hawkes
Hawkes is the surname of Sylvia Ashley, a British model, actress, and socialite known for her high-profile marriages in the early 20th century.
E188303 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: Hawkes | Statement: [Sylvia Ashley, familyName, Hawkes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hawkes
Context triple: [Sylvia Ashley, familyName, Hawkes]
  • A. Nighthawk
    Nighthawk is the radio callsign used by Marine Helicopter Squadron One (HMX-1), the U.S. Marine Corps unit responsible for transporting the President of the United States.
  • B. Hawk
    The Hawk is a bird of prey commonly symbolizing keen vision, strength, and agility, and serves as the mascot for various schools and sports teams.
  • C. Holloway
    Holloway is a district in the London Borough of Islington, England, known for its urban character and as the area surrounding Arsenal FC’s Emirates Stadium.
  • D. The Eagle
    The Eagle is a 1925 silent adventure film starring Rudolph Valentino as a dashing Russian outlaw hero.
  • E. Kestrel
    Kestrel is a cross-platform, high-performance web server built into ASP.NET Core for hosting and serving web applications.
  • 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: Hawkes
Triple: [Sylvia Ashley, familyName, Hawkes]
Generated description
Hawkes is the surname of Sylvia Ashley, a British model, actress, and socialite known for her high-profile marriages in the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hawkes
Target entity description: Hawkes is the surname of Sylvia Ashley, a British model, actress, and socialite known for her high-profile marriages in the early 20th century.
  • A. Nighthawk
    Nighthawk is the radio callsign used by Marine Helicopter Squadron One (HMX-1), the U.S. Marine Corps unit responsible for transporting the President of the United States.
  • B. Hawk
    The Hawk is a bird of prey commonly symbolizing keen vision, strength, and agility, and serves as the mascot for various schools and sports teams.
  • C. Holloway
    Holloway is a district in the London Borough of Islington, England, known for its urban character and as the area surrounding Arsenal FC’s Emirates Stadium.
  • D. The Eagle
    The Eagle is a 1925 silent adventure film starring Rudolph Valentino as a dashing Russian outlaw hero.
  • E. Kestrel
    Kestrel is a cross-platform, high-performance web server built into ASP.NET Core for hosting and serving web applications.
  • 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_69a8861286808190939afff3ce8ee31e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa61e142ac8190aa2fbd8f0826b5b2 completed March 6, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad683461ec8190b442054443c472b3 completed March 8, 2026, 12:14 p.m.
NEDg Description generation batch_69ad693c04bc8190acc3566472a773f7 completed March 8, 2026, 12:19 p.m.
NED2 Entity disambiguation (via description) batch_69ad69b46fe88190a4dc1568cabc69b6 completed March 8, 2026, 12:21 p.m.
Created at: March 4, 2026, 7:29 p.m.