Triple
T18737184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wallace Beery |
E458194
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Carol Ann Beery |
E458194
|
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: Carol Ann Beery | Statement: [Wallace Beery, child, Carol Ann Beery]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Ann Beery Context triple: [Wallace Beery, child, Carol Ann Beery]
-
A.
Carol Ann Beery
chosen
Carol Ann Beery is the daughter of Academy Award–winning American actor Wallace Beery.
-
B.
Betsy Beers
Betsy Beers is an American television and film producer best known for her longtime collaboration with Shonda Rhimes on hit series such as Grey’s Anatomy and Scandal.
-
C.
Joan Beal
Joan Beal is an American vocalist and musician known for her work as a jazz singer and for frequent collaborations with her husband, composer Jeff Beal.
-
D.
Barbara Boothe
Barbara Boothe is an American woman best known as the mother of film producer and Skydance Media founder David Ellison.
-
E.
Ruth Byerly
Ruth Byerly is known primarily as the first wife of American television executive and producer Grant Tinker.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e57689fa508190ad821d361cba9edf |
completed | April 20, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05be39f18c8190b740f066ab69d52b |
completed | May 14, 2026, 12:21 p.m. |
Created at: April 10, 2026, 11:51 a.m.