Triple
T15689833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie Kennedy Clark |
E380297
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Dena Clark |
E1250364
|
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: Dena Clark | Statement: [Sophie Kennedy Clark, mother, Dena Clark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dena Clark Context triple: [Sophie Kennedy Clark, mother, Dena Clark]
-
A.
Dena Clark
chosen
Dena Clark is a relative of Scottish actress Sophie Kennedy Clark, who is known for her roles in independent and art-house films.
-
B.
Lisa Clark
Lisa Clark is an American businesswoman and socialite best known for her former marriage to music executive Tommy Mottola.
-
C.
Dena Kaye
Dena Kaye is the daughter of famed American entertainer Danny Kaye and has been involved in preserving and promoting her father's legacy.
-
D.
Amanda Clayton
Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
-
E.
Marisa Clark
Marisa Clark is a fun-loving, fashion-conscious best friend and sidekick to the main character in the Disney Channel spy-comedy series "K.C. Undercover."
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4e59988190aaf12f6a07c8f0e4 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014134601c81909f7f4a95d558e067 |
completed | May 11, 2026, 2:38 a.m. |
Created at: April 10, 2026, 4:44 a.m.