Triple
T26153309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savonlinna Opera Festival |
E659885
|
entity |
| Predicate | firstPerformancesHeldAt |
P58338
|
FINISHED |
| Object | Olavinlinna Castle courtyard |
—
|
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: Olavinlinna Castle courtyard | Statement: [Savonlinna Opera Festival, firstPerformancesHeldAt, Olavinlinna Castle courtyard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPerformancesHeldAt Context triple: [Savonlinna Opera Festival, firstPerformancesHeldAt, Olavinlinna Castle courtyard]
-
A.
firstPerformanceAt
chosen
Indicates the location or event at which an entity (such as a work or performance) was first performed.
-
B.
firstPerformanceFestival
Indicates the festival at which an entity (such as a work or performance) was first publicly performed.
-
C.
firstPerformanceBy
Indicates that the referenced performance is the earliest or debut performance carried out by the specified entity.
-
D.
firstPerformanceTheatre
Indicates the theatre where an entity (such as a play or performance) was first performed.
-
E.
firstPerformanceCityOfWork
Indicates the city where a particular work was first performed.
- 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_69ee5bc5a9908190899d39ce95c6d215 |
completed | April 26, 2026, 6:39 p.m. |
| NER | Named-entity recognition | batch_69fddac4e2f48190a9301d3422658b29 |
completed | May 8, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69fdda06969c8190b5d033964ea2a690 |
completed | May 8, 2026, 12:41 p.m. |
Created at: April 26, 2026, 8:26 p.m.