Triple
T789590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Number One Observatory Circle |
E16880
|
entity |
| Predicate | notOpenTo |
P13175
|
FINISHED |
| Object | general public |
—
|
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: general public | Statement: [Number One Observatory Circle, notOpenTo, general public]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notOpenTo Context triple: [Number One Observatory Circle, notOpenTo, general public]
-
A.
openedForPublic
Indicates that something has been made accessible or available for use, entry, or participation by the general public.
-
B.
membershipOpenTo
Indicates that joining or belonging to a group, organization, or category is permitted for the specified entities or audience.
-
C.
notAccessibleBy
chosen
Indicates that one entity cannot be reached, used, or obtained through another specified entity or means.
-
D.
isOpenTo
Indicates that one entity is receptive, willing, or available to consider, accept, or engage with another entity or proposal.
-
E.
opens
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a7841b0c8190859ecd247e32c6ec |
completed | March 1, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69a4a50ef72c819084ffe9f31dbd0262 |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:38 p.m.