Triple
T21991126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krypto the Superdog |
E543091
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Otto Binder |
—
|
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: Otto Binder | Statement: [Krypto the Superdog, creator, Otto Binder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Otto Binder Context triple: [Krypto the Superdog, creator, Otto Binder]
-
A.
Otto Binder
chosen
Otto Binder was a prolific American science fiction and comic book writer best known for his influential work on Captain Marvel and Superman-related stories during the Golden Age of comics.
-
B.
Erich Pleskoff
Erich Pleskoff is the birth name of Eric Pleskow, the Austrian-born American film producer and former president of United Artists and Orion Pictures.
-
C.
Irving Gertz
Irving Gertz was an American film composer known for scoring mid-20th-century Hollywood movies, particularly war and science fiction films.
-
D.
Leonard Goldberg
Leonard Goldberg was an American television and film producer known for creating and overseeing numerous popular series and movies from the 1960s onward.
-
E.
Robert Tomarkin
Robert Tomarkin was the husband of Academy Award–winning American actress Dorothy Malone.
- 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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1270d7cbc819086eea86be04a2ec0 |
completed | April 28, 2026, 9:30 p.m. |
Created at: April 16, 2026, 8:05 p.m.