Triple
T29300411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanban |
E742940
|
entity |
| Predicate | alternateScriptWriter |
P53375
|
FINISHED |
| Object | Madhan Karky |
—
|
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: Madhan Karky | Statement: [Nanban, alternateScriptWriter, Madhan Karky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alternateScriptWriter Context triple: [Nanban, alternateScriptWriter, Madhan Karky]
-
A.
scriptWriter
chosen
Indicates that one entity is the person who wrote or authored the script associated with another entity.
-
B.
usesScriptFor
Indicates that one entity employs or relies on a particular script or writing system for its representation, communication, or operation.
-
C.
formerScript
Indicates that an entity previously served as the script or writing system for another entity, but is no longer used in that role.
-
D.
scriptEvolution
Indicates how a script or written system changes, develops, or transforms over time in relation to its earlier or later forms.
-
E.
animeScriptwriter
Indicates that one entity is the scriptwriter responsible for writing or composing the script of an anime associated with the other entity.
- 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_69f09123ed9881909f351f7541933f5e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 1:09 p.m.