Triple
T24934532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 9 by 5 Impression Exhibition |
E623276
|
entity |
| Predicate | approximateDimensionsOfWorks |
P162556
|
FINISHED |
| Object | 9 by 5 inches |
—
|
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: 9 by 5 inches | Statement: [9 by 5 Impression Exhibition, approximateDimensionsOfWorks, 9 by 5 inches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateDimensionsOfWorks Context triple: [9 by 5 Impression Exhibition, approximateDimensionsOfWorks, 9 by 5 inches]
-
A.
approximateNumberOfWorks
Indicates an estimated or roughly calculated count of works associated with an entity.
-
B.
numberOfWorks
Indicates the total count of works associated with a given entity.
-
C.
estimatedNumberOfPaintings
Indicates the approximate count of paintings associated with an entity, rather than an exact, verified number.
-
D.
formatOfWorks
Indicates the specific medium, layout, or structural form in which works are created, presented, or published.
-
E.
typeOfWorksListed
Indicates that the kinds or categories of works associated with an entity are specified or enumerated.
- F. None of above. chosen
Provenance (4 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_69e2fac6b5a48190a1c38857f00915a9 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f62b9e5ba88190a3c0d46edec7afe7 |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f627ad6d4c81909796d39d78e414f9 |
completed | May 2, 2026, 4:34 p.m. |
Created at: April 18, 2026, 5:30 a.m.