Triple
T14247631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giacometti collection |
E353175
|
entity |
| Predicate | hasTimeCoverage |
P3058
|
FINISHED |
| Object | 20th century art |
—
|
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: 20th century art | Statement: [Giacometti collection, hasTimeCoverage, 20th century art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTimeCoverage Context triple: [Giacometti collection, hasTimeCoverage, 20th century art]
-
A.
hasFrequencyCoverage
Indicates that one entity provides, supports, or is applicable across a specified range or set of frequencies associated with another entity.
-
B.
hasCoverage
Indicates that one entity provides insurance or protection coverage for another entity or subject.
-
C.
timePeriodCoveredTo
chosen
Indicates the span or duration of time that is encompassed, addressed, or relevant to a given subject or entity.
-
D.
timeHorizonCovered
Indicates the span or duration of time that is encompassed or addressed by something (such as a plan, forecast, or agreement).
-
E.
hasBeenCoveredBy
Indicates that something has received coverage or treatment by another entity, such as being reported on, discussed, or addressed.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de629464f88190817b190731bab156 |
completed | April 14, 2026, 3:51 p.m. |
| PD | Predicate disambiguation | batch_69de05c09b7881908acbca18bd7d997c |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:08 a.m.