Triple
T16845681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidential Palace |
E409531
|
entity |
| Predicate | mayBeOpenFor |
P2556
|
FINISHED |
| Object | official state visits |
—
|
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: official state visits | Statement: [Presidential Palace, mayBeOpenFor, official state visits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeOpenFor Context triple: [Presidential Palace, mayBeOpenFor, official state visits]
-
A.
isOpenTo
chosen
Indicates that one entity is receptive, willing, or available to consider, accept, or engage with another entity or proposal.
-
B.
hasOpening
Indicates that one entity possesses or features an opening, gap, or entrance that allows access, passage, or exposure.
-
C.
hasOpenedFor
Indicates that one entity has performed or appeared as the opening act or preliminary participant for another entity, typically in an event or performance context.
-
D.
openedForUse
Indicates that something has been made accessible and available for its intended operation or use.
-
E.
canBeOpenedBy
Indicates that one entity has the ability or permission to open 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b3541a008190b2a97cfea92b170f |
completed | April 18, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.