Triple
T28724202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | English Staircase |
E730176
|
entity |
| Predicate | isInteriorFeatureOf |
P6655
|
FINISHED |
| Object | Dresden Castle |
E197906
|
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: Dresden Castle | Statement: [English Staircase, isInteriorFeatureOf, Dresden Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInteriorFeatureOf Context triple: [English Staircase, isInteriorFeatureOf, Dresden Castle]
-
A.
withinFeature
Indicates that one entity is spatially contained inside or lies entirely within the bounds of another feature.
-
B.
isFeatureOf
Indicates that something functions as a characteristic, attribute, or component belonging to or describing another entity.
-
C.
hasInteriorFeature
chosen
Indicates that an entity contains or includes a specific feature within its interior space.
-
D.
locatedInTheInteriorOf
Indicates that one entity is situated entirely within the inner part or inside area of another entity, rather than on its surface or boundary.
-
E.
isAComponentOf
Indicates that one entity functions as a constituent part or sub-unit of another, larger entity.
- 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_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a25d8f25bc881909cc0762ae16d3264 |
completed | June 7, 2026, 8:47 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 5:55 a.m.