Triple
T31965804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Brunwald |
E816170
|
entity |
| Predicate | hasOnScreenDestruction |
P180451
|
FINISHED |
| Object | partially damaged during escape |
—
|
LITERAL 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: partially damaged during escape | Statement: [Castle Brunwald, hasOnScreenDestruction, partially damaged during escape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOnScreenDestruction Context triple: [Castle Brunwald, hasOnScreenDestruction, partially damaged during escape]
-
A.
hasOnScreenDynamic
Indicates that one entity displays or presents another entity as a changing or interactive element on a screen.
-
B.
hasOnScreenRelative
Indicates that one entity has a family member who appears or is depicted on screen in relation to it.
-
C.
hasOnscreenFunction
Indicates that an entity serves a particular role or performs a specific function when it appears on screen.
-
D.
hasOnScreenOwner
Indicates that an entity is owned or controlled by another entity that is explicitly shown or represented on screen.
-
E.
hasOnScreenConflictWith
Indicates that two entities are depicted as being in conflict or opposition with each other within an on-screen or visual context.
- F. None of above. chosen
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_69f348f5ae5481909da0247869f51955 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
| PDg | Predicate description generation | batch_69f74061c440819080434155c2d60341 |
completed | May 3, 2026, 12:32 p.m. |
Created at: May 1, 2026, 12:09 a.m.