Triple
T17415107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alan Howard |
E423468
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Leslie Howard |
—
|
NE NERFINISHED |
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: Leslie Howard | Statement: [Alan Howard, relative, Leslie Howard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leslie Howard Context triple: [Alan Howard, relative, Leslie Howard]
-
A.
Leslie Howard
chosen
Leslie Howard was a British actor and filmmaker best known for his role as Ashley Wilkes in the classic film "Gone with the Wind."
-
B.
Jack Hawkins
Jack Hawkins was a distinguished British actor known for his commanding presence in mid-20th-century war and historical films.
-
C.
George Powell
George Powell was a 19th-century British sealer and explorer noted for his Antarctic voyages and co-discovery of several sub-Antarctic islands.
-
D.
Henry Donovan
Henry Donovan is a fictional character from the television series "24: Legacy," involved in the show's high-stakes counterterrorism drama.
-
E.
George Brent
George Brent was an Irish-American leading man of 1930s and 1940s Hollywood cinema, known for his suave screen presence opposite stars like Bette Davis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44231e29881909695a33aab1d49a2 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.