Triple
T11983341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raya and the Last Dragon |
E285212
|
entity |
| Predicate | storyBy |
P1955
|
FINISHED |
| Object | Paul Briggs |
E810536
|
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: Paul Briggs | Statement: [Raya and the Last Dragon, storyBy, Paul Briggs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Briggs Context triple: [Raya and the Last Dragon, storyBy, Paul Briggs]
-
A.
Paul Briggs
chosen
Paul Briggs is an American animator, storyboard artist, and voice actor best known for his work on Disney animated films such as Frozen and Big Hero 6.
-
B.
Douglas Roberts
Douglas Roberts is known primarily as one of the sons of American cable television pioneer and Comcast co-founder Ralph J. Roberts.
-
C.
Robert Fletcher
Robert Fletcher was an American costume designer best known for creating the iconic uniforms and outfits for the early Star Trek films.
-
D.
Patrick Haggard
Patrick Haggard is a cognitive neuroscientist known for his research on voluntary action, motor control, and the sense of agency in the human brain.
-
E.
Richard Scudder
Richard Scudder was an American newspaper executive and co-founder of MediaNews Group, known for his influential role in the U.S. newspaper industry.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903973c848190aac871d6dfecc74b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f48aa73458819097a69b371350743c |
completed | May 1, 2026, 11:12 a.m. |
Created at: April 8, 2026, 9:46 p.m.