Triple
T27485807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahmut Pasha Bazaar |
E693731
|
entity |
| Predicate | openAirOrCovered |
P47415
|
FINISHED |
| Object | partly covered |
—
|
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: partly covered | Statement: [Mahmut Pasha Bazaar, openAirOrCovered, partly covered]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openAirOrCovered Context triple: [Mahmut Pasha Bazaar, openAirOrCovered, partly covered]
-
A.
isEnclosedWhenRoofClosed
Indicates that one entity is completely contained or surrounded by another whenever the roof is in its closed position.
-
B.
hasOutdoorSpaceType
Indicates the specific kind of outdoor area associated with an entity, such as a balcony, terrace, garden, or patio.
-
C.
roofedForProtection
Indicates that something is provided with a roof or overhead covering specifically to shield or protect it from external elements or hazards.
-
D.
isOpenAir
chosen
Indicates that something takes place or exists in an outdoor, unenclosed environment exposed to open air.
-
E.
openSpaceType
Indicates the type or category of an open space associated with an entity (e.g., park, plaza, courtyard).
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e848b008190bd7314c9a0f884a3 |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:02 p.m.