Triple
T7809338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speedy |
E180637
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Brooks Benedict |
E694525
|
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: Brooks Benedict | Statement: [Speedy, hasCastMember, Brooks Benedict]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brooks Benedict Context triple: [Speedy, hasCastMember, Brooks Benedict]
-
A.
Brooks Benedict
chosen
Brooks Benedict was an American film actor active during the silent and early sound eras, known for his supporting roles in numerous 1920s and 1930s movies.
-
B.
Samuel Miles
Samuel Miles was an American Revolutionary War officer and early political figure from Pennsylvania who later served as a judge and mayor of Philadelphia.
-
C.
Spencer Dryden
Spencer Dryden was an American drummer best known for his influential work with the psychedelic rock band Jefferson Airplane during the late 1960s.
-
D.
Jean Brooks
Jean Brooks was an American film actress of the 1930s and 1940s, best known for her roles in horror and mystery films produced by RKO Pictures.
-
E.
Murray Bartlett
Murray Bartlett is an Australian actor best known for his acclaimed performances in television series such as "Looking," "The White Lotus," and "The Last of Us."
- 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_69ca827f6f148190beca4e245b993506 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf78bb4b08190b2b3b51c5a0a033c |
completed | March 30, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5a4724288190b6f18f8cdde080ed |
completed | March 31, 2026, 5:23 a.m. |
Created at: March 30, 2026, 4:36 p.m.