Triple
T22383256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Waterworks (Altes Wasserwerk) |
E553326
|
entity |
| Predicate | ownerContext |
P347
|
FINISHED |
| Object | publicly owned facility in Bonn |
—
|
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: publicly owned facility in Bonn | Statement: [Old Waterworks (Altes Wasserwerk), ownerContext, publicly owned facility in Bonn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownerContext Context triple: [Old Waterworks (Altes Wasserwerk), ownerContext, publicly owned facility in Bonn]
-
A.
organizationContext
Indicates that one entity operates within, is associated with, or is relevant to the organizational setting or environment defined by another entity.
-
B.
originContext
Indicates the situational or environmental circumstances from which an entity, event, or piece of information originates.
-
C.
ownerPosition
Indicates the spatial or positional relationship of an owner relative to the owned entity.
-
D.
targetOwnership
Indicates that one entity holds ownership or proprietary control over the target entity.
-
E.
ownedBy
chosen
Indicates that one entity possesses legal or rightful ownership of another 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1582d8e548190a7330de49d519675 |
completed | April 29, 2026, 1 a.m. |
| PD | Predicate disambiguation | batch_69e73015484c8190a9a0b9f554b61a81 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:45 p.m.