Triple
T26087042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radziwill Palace |
E658011
|
entity |
| Predicate | servedAsVenueFor |
P122061
|
FINISHED |
| Object | Congress of Berlin |
—
|
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: Congress of Berlin | Statement: [Radziwill Palace, servedAsVenueFor, Congress of Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedAsVenueFor Context triple: [Radziwill Palace, servedAsVenueFor, Congress of Berlin]
-
A.
hasVenueFor
Indicates that one entity provides or serves as the location or setting where an event, activity, or function takes place for another entity.
-
B.
hasHostedVenue
Indicates that a particular venue has served as the location for hosting a specific event or activity.
-
C.
hasVenueIn
Indicates that an event, activity, or occurrence takes place at a specific venue located within a particular geographic area or location.
-
D.
notableEventHostedAtReferredVenue
chosen
Indicates that a notable event was hosted at, or took place in, the referenced venue.
-
E.
performedAtVenue
Indicates that an event or performance took place at a specific venue or location.
- 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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 26, 2026, 7:43 p.m.