Triple
T29083005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marvel Preview #7 |
E734027
|
entity |
| Predicate | hasDebutCharacter |
P116161
|
FINISHED |
| Object | Rocket Raccoon |
—
|
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: Rocket Raccoon | Statement: [Marvel Preview #7, hasDebutCharacter, Rocket Raccoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDebutCharacter Context triple: [Marvel Preview #7, hasDebutCharacter, Rocket Raccoon]
-
A.
hasOnScreenDebutActor
Indicates that an actor makes their first on-screen appearance in the referenced work or production.
-
B.
featuresCharacterDebut
chosen
Indicates that the subject work includes the first-ever appearance of a particular character.
-
C.
debutAs
Indicates that an entity makes its first public appearance or introduction in a particular role, medium, or context.
-
D.
marksDebutOfCharacter
Indicates that an event, work, or appearance represents the first introduction of a particular character.
-
E.
stageDebutRole
Indicates the role in which an entity first appeared in a stage performance or theatrical debut.
- F. None of above.
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_69f05b0c0f28819086eae6e84f2ae472 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fd19f791f48190bbb6f6047f9ddc59 |
completed | May 7, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fd0df365948190bc9bfc7ffd46acd8 |
completed | May 7, 2026, 10:10 p.m. |
Created at: April 28, 2026, 10:57 a.m.