Triple
T23013416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | course runs along St. Petersburg waterfront |
E572965
|
entity |
| Predicate | closedToPublicDuringEvent |
P77024
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [course runs along St. Petersburg waterfront, closedToPublicDuringEvent, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedToPublicDuringEvent Context triple: [course runs along St. Petersburg waterfront, closedToPublicDuringEvent, true]
-
A.
closedDuring
Indicates that an entity is not open or available for use during a specified time period or under certain conditions.
-
B.
closedCityDuring
Indicates that a city is not accessible or operational during a specified time period or interval.
-
C.
closedVenue
Indicates that a venue is not open or available for use during a given time or event.
-
D.
closedToPublic
chosen
Indicates that access to the referenced entity is restricted so that the general public is not allowed to enter or use it.
-
E.
closedAfterEvent
Indicates that an entity becomes or is marked as closed following the occurrence of a specified event.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e300008190bb12c6388a8b3280 |
completed | April 29, 2026, 4:06 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:51 p.m.