Triple
T13848162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ted Stevens |
E332862
|
entity |
| Predicate | hasSpouse |
P13
|
FINISHED |
| Object | Ann Cherrington |
E332862
|
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: Ann Cherrington | Statement: [Ted Stevens, hasSpouse, Ann Cherrington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Cherrington Context triple: [Ted Stevens, hasSpouse, Ann Cherrington]
-
A.
Ann Cherrington
chosen
Ann Cherrington is best known as the wife of the late U.S. Senator Ted Stevens of Alaska.
-
B.
Jean Crouch
Jean Crouch was the first wife of long-serving U.S. Senator Strom Thurmond, whom he married after meeting her when she was crowned Miss South Carolina.
-
C.
Cheryl Edwards
Cheryl Edwards is a screenwriter best known for her work on the film "In the Mix."
-
D.
Jay Vivian Chambers
Jay Vivian Chambers was an American writer and former Soviet spy who became a key witness in the Alger Hiss espionage case during the early Cold War.
-
E.
Ellise Chappell
Ellise Chappell is an English actress known for her roles in film and television, including the romantic comedy "Yesterday" and the period drama series "Poldark."
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02b2a9788190b164760adec64ef6 |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac802b7081909b36eebe85374594 |
completed | May 6, 2026, 9:02 p.m. |
Created at: April 9, 2026, 10:14 p.m.