Triple
T1321352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parc des Bastions |
E28224
|
entity |
| Predicate | hasOpeningPolicy |
P17856
|
FINISHED |
| Object | open year-round |
—
|
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: open year-round | Statement: [Parc des Bastions, hasOpeningPolicy, open year-round]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOpeningPolicy Context triple: [Parc des Bastions, hasOpeningPolicy, open year-round]
-
A.
hasOpeningType
chosen
Indicates that one entity has, features, or is characterized by a particular type or kind of opening.
-
B.
hasReservationPolicy
Indicates that an entity specifies or is governed by a particular policy regarding how reservations are made, managed, or honored.
-
C.
isOpenTo
Indicates that one entity is receptive, willing, or available to consider, accept, or engage with another entity or proposal.
-
D.
hasVisitorPolicy
Indicates that an entity has an established policy governing the presence, behavior, or permissions of visitors.
-
E.
openedForUse
Indicates that something has been made accessible and available for its intended operation or use.
- 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19932888190a3d45871e84f112e |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beedb49c8190beb5b85cdda05013 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.