Triple
T10811904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dooley Wilson |
E255122
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Arthur Wilson |
E326587
|
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: Arthur Wilson | Statement: [Dooley Wilson, birthName, Arthur Wilson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arthur Wilson Context triple: [Dooley Wilson, birthName, Arthur Wilson]
-
A.
Arthur Wilson
chosen
Arthur Wilson, better known by his stage name Dooley Wilson, was an American actor and singer most famous for performing "As Time Goes By" as Sam in the classic film Casablanca.
-
B.
Frank Wilson
Frank Wilson was an American songwriter and record producer best known for his influential work with Motown Records in the 1960s and 1970s.
-
C.
Albert Webster
Albert Webster was the husband of Una Hawthorne, the daughter of American novelist Nathaniel Hawthorne.
-
D.
John Williams Wilson
John Williams Wilson was a 19th-century Chilean naval officer of British origin who played a key role in Chile’s southern maritime exploration and settlement.
-
E.
Michael Wilson
Michael Wilson was a film producer best known for his work on classic mid-20th-century American Westerns and dramas.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733eadda48190b2b1183ee60102cb |
completed | April 9, 2026, 5:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e42d4ab9bc81908a2522d1334390fc |
completed | April 19, 2026, 1:18 a.m. |
Created at: April 8, 2026, 9:18 p.m.