Triple
T5515140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Grant Sherry |
E144662
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | William Grant Sherry |
E144662
|
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: William Grant Sherry | Statement: [William Grant Sherry, name, William Grant Sherry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Grant Sherry Context triple: [William Grant Sherry, name, William Grant Sherry]
-
A.
William Grant Sherry
chosen
William Grant Sherry was an American artist and World War II veteran best known as the third husband of actress Bette Davis.
-
B.
Charles Black
Charles Black is a business associate and partner of Adam Black.
-
C.
George Rex Graham
George Rex Graham was a 19th-century American editor and publisher best known for founding and running Graham's Magazine, an influential literary periodical that featured works by authors such as Edgar Allan Poe.
-
D.
Day Hennessy
Day Hennessy is a surname associated with the individual Tamar Teresa Day Hennessy.
-
E.
William Kerr
William Kerr is a film editor known for his work on major Hollywood comedies, including "The Five-Year Engagement."
- 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_69c008f77ff88190b0cd50ca207295d1 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f5d1d188190b3a222a9ecf2a0e6 |
completed | March 22, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c027d92e0c8190ad5552d66e370a22 |
completed | March 22, 2026, 5:33 p.m. |
Created at: March 22, 2026, 3:33 p.m.