Triple
T21017212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Office Building (Juneau) |
E517709
|
entity |
| Predicate | floorSpaceUse |
P68010
|
FINISHED |
| Object | administrative offices |
—
|
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: administrative offices | Statement: [State Office Building (Juneau), floorSpaceUse, administrative offices]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floorSpaceUse Context triple: [State Office Building (Juneau), floorSpaceUse, administrative offices]
-
A.
floorAreaFeature
Indicates a relationship where a specific feature or characteristic is associated with the floor area of an entity or space.
-
B.
floorCountAroundSpace
Indicates the number of floors present in the vicinity of a given space or area.
-
C.
hasFloorArea
Indicates that an entity possesses a specified amount of floor space as a measurable area.
-
D.
floorUseDistribution
Indicates how the use or function of space is distributed across different floors or levels within a structure.
-
E.
hasFloorUse
chosen
Indicates that a particular floor or level of a building is designated for a specific function, activity, or type of 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5968c081909ae6407199858aba |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf274ac81909bbf245627dc8fdc |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:54 p.m.