Triple
T19465025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Africa Screams |
E486970
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Clyde Beatty |
—
|
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: Clyde Beatty | Statement: [Africa Screams, starring, Clyde Beatty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clyde Beatty Context triple: [Africa Screams, starring, Clyde Beatty]
-
A.
Clyde Beatty
chosen
Clyde Beatty was a famous American animal trainer and circus performer known for his daring big-cat acts and appearances in early adventure films.
-
B.
Victor Saville
Victor Saville was a British film director and producer known for his work in both the UK and Hollywood during the early to mid-20th century.
-
C.
Carl Hagenbeck
Carl Hagenbeck was a pioneering German animal dealer and zoo director known for revolutionizing modern zoo design with open, cageless enclosures and for organizing ethnographic exhibitions in the late 19th and early 20th centuries.
-
D.
Joseph Bale
Joseph Bale is the son of actor Christian Bale and his wife, Sibi Blazic.
-
E.
Santos Irwin
Santos Irwin is the child of American actor and clown Bill Irwin.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633d0fe3c8190b637f78bfad704d0 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:39 p.m.