Triple
T34108937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Next Karate Kid |
E874783
|
entity |
| Predicate | featuresCharacterReturningFromPreviousFilms |
P192356
|
FINISHED |
| Object | Mr. Miyagi |
E521429
|
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: Mr. Miyagi | Statement: [The Next Karate Kid, featuresCharacterReturningFromPreviousFilms, Mr. Miyagi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCharacterReturningFromPreviousFilms Context triple: [The Next Karate Kid, featuresCharacterReturningFromPreviousFilms, Mr. Miyagi]
-
A.
featuresReturningCharacterFrom
chosen
Indicates that a work includes the reappearance of a character who previously appeared in the referenced source work.
-
B.
featuresReturnOf
Indicates that something (such as a work, event, or product) includes or highlights the comeback or reappearance of a person, character, element, or feature.
-
C.
featuresCharactersFrom
Indicates that one entity (such as a work or production) includes or presents characters originating from another entity.
-
D.
filmCharacterOf
Indicates that a person or character is a character appearing in a specified film.
-
E.
leadCharacterPreviouslyAppearedIn
Indicates that the lead character of the current work has appeared before in a prior work or context.
- F. None of above.
Provenance (4 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_69f349a80d4481908527317d43f5c579 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a02ff7de1d881909c29729f2a771381 |
completed | May 12, 2026, 10:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36d5ce7a6481908fae2bbc3356df57 |
completed | June 20, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_6a02fd1c45c48190bf9dbd91acaeee9f |
completed | May 12, 2026, 10:12 a.m. |
Created at: May 1, 2026, 1:53 a.m.