Triple
T14961116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akari light sculptures |
E373065
|
entity |
| Predicate | hasSeriesSize |
P80358
|
FINISHED |
| Object | over 100 different models |
—
|
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: over 100 different models | Statement: [Akari light sculptures, hasSeriesSize, over 100 different models]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSeriesSize Context triple: [Akari light sculptures, hasSeriesSize, over 100 different models]
-
A.
hasSeriesStructure
Indicates that one entity is organized as a sequence or series of related components or parts.
-
B.
hasSize
Indicates that one entity possesses a particular physical magnitude or extent, such as length, volume, or overall dimensions.
-
C.
hasSeriesDefinition
Indicates that something is associated with a specific series-level definition that characterizes or constrains it.
-
D.
seriesSize
chosen
Indicates the total number of items or installments that make up a complete series.
-
E.
hasSeriesNumber
Indicates that an entity is assigned a specific ordinal or sequence number within a series or ordered set.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cece6881908cd8c8fe41583bee |
completed | April 15, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:40 a.m.