Triple
T9856183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Window on Washington Waters |
E239591
|
entity |
| Predicate | exhibitMedium |
P47681
|
FINISHED |
| Object | large viewing window |
—
|
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: large viewing window | Statement: [Window on Washington Waters, exhibitMedium, large viewing window]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exhibitMedium Context triple: [Window on Washington Waters, exhibitMedium, large viewing window]
-
A.
exhibitionMedium
chosen
Indicates the material or format through which something is exhibited or displayed.
-
B.
exhibitionScale
Indicates the relative size, scope, or extent of an exhibition in which an entity is presented or involved.
-
C.
exhibitedBy
Indicates that something (such as a quality, behavior, or characteristic) is shown, displayed, or demonstrated by a particular entity.
-
D.
exhibition
Indicates that an entity is organizing, hosting, or serving as a public display or presentation of another entity (such as artworks, objects, or information).
-
E.
exhibitionUse
Indicates that something is used, intended, or designated for display in an exhibition or exhibit context.
- 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_69ca84e6493081909cf58c8d42ea856b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb39719288190adf45e7c029edd51 |
completed | April 2, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:35 p.m.