Triple
T8068438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sylvia Ashley |
E188303
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hawkes |
E188303
|
NE FINISHED |
How this triple was built (2 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.
Hawkes
chosen
Hawkes is the surname of Sylvia Ashley, a British model, actress, and socialite known for her high-profile marriages in the early 20th century.
-
B.
The Hawk
The Hawk was the nickname of Connie Hawkins, a Hall of Fame American basketball player renowned for his spectacular leaping ability and creative, acrobatic play.
-
C.
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.
-
D.
Nighthawk
Nighthawk is a flying steel roller coaster at the Carowinds amusement park known for its face-down riding position and multiple inversions.
-
E.
Moxey
Moxey is a shy, hapless bricklayer and one of the central members of the group of British migrant workers in the comedy-drama series "Auf Wiedersehen, Pet."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ff8a4fc8190a97fc7111ca7ec4d |
completed | March 31, 2026, 3:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63e587908190980f1f026f4aa153 |
completed | April 1, 2026, 12:16 a.m. |
Created at: March 30, 2026, 5:27 p.m.