Triple
T16425798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William J. Casey |
E398939
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sophia Kurz Casey |
E304802
|
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: Sophia Kurz Casey | Statement: [William J. Casey, spouse, Sophia Kurz Casey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sophia Kurz Casey Context triple: [William J. Casey, spouse, Sophia Kurz Casey]
-
A.
Sophia Kurz Casey
chosen
Sophia Kurz Casey was the wife of former CIA Director William J. Casey and a prominent Washington, D.C. hostess and political insider.
-
B.
Sophia Johnson
Sophia Johnson was the wife of American industrialist and railroad magnate Cornelius Vanderbilt, with whom she had a large family during the early 19th century.
-
C.
Sophia Johnson
Sophia Johnson is a person whose specific public identity or notable achievements are not clearly defined from the given information.
-
D.
Casey Davenport
Casey Davenport is a character from the animated series "Wings," likely serving as one of the show's central or recurring figures.
-
E.
Casey
Casey is a witty, outspoken best friend character in the romantic comedy film "27 Dresses," known for providing comic relief and candid advice to the protagonist.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e328faa7448190a2606f1b37ea0a3d |
completed | April 18, 2026, 6:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c7273e48190b0668948141cf30b |
completed | May 10, 2026, 8:06 a.m. |
Created at: April 10, 2026, 5:09 a.m.