Triple
T8076166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shot Sage Blue Marilyn |
E188495
|
entity |
| Predicate | seriesSize |
P80358
|
FINISHED |
| Object | 4 paintings in the Shot Marilyns series |
—
|
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: 4 paintings in the Shot Marilyns series | Statement: [Shot Sage Blue Marilyn, seriesSize, 4 paintings in the Shot Marilyns series]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seriesSize Context triple: [Shot Sage Blue Marilyn, seriesSize, 4 paintings in the Shot Marilyns series]
-
A.
numberOfSeries
Indicates the total count of distinct series associated with or contained within a given entity.
-
B.
seriesScale
Indicates that one value or measurement is expressed relative to another according to a defined proportional scale within a series.
-
C.
seriesBy
Indicates that one entity is the creator, author, or originator of a series to which the other entity belongs.
-
D.
seriesOf
Indicates that one entity is a sequence or ordered set of related items, events, or parts that collectively form or belong to another entity.
-
E.
hasSeriesNumber
Indicates that an entity is assigned a specific ordinal or sequence number within a series or ordered set.
- 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_69ca82b50c708190863f661d438e68df |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb404dc7ac8190956b5c2f5aeac6b2 |
completed | March 31, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69cb049f1614819087360d1a4c6f0faa |
completed | March 30, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69cb14be17208190bb51c3dfcb613f20 |
completed | March 31, 2026, 12:26 a.m. |
Created at: March 30, 2026, 5:28 p.m.