Triple
T24205280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Picasso’s harlequin paintings |
E600087
|
entity |
| Predicate | chronologicallySpans |
P32028
|
FINISHED |
| Object | Picasso’s Blue Period |
—
|
NE NERFINISHED |
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: Picasso’s Blue Period | Statement: [Picasso’s harlequin paintings, chronologicallySpans, Picasso’s Blue Period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chronologicallySpans Context triple: [Picasso’s harlequin paintings, chronologicallySpans, Picasso’s Blue Period]
-
A.
chronologicallyCovers
chosen
Indicates that one time period, event, or sequence extends over and includes the entire chronological span of another.
-
B.
chronologicallyOrdered
Indicates that the related entities are arranged in the order in which they occur in time.
-
C.
chronologicallyOrders
Indicates that one entity arranges or sequences other entities according to their positions in time, from earlier to later.
-
D.
chronologyIncludes
Indicates that a broader chronological sequence or timeline encompasses a specific time span, event, or period as part of it.
-
E.
chronologicallyAmong
Indicates that one event or time point occurs within the temporal range defined by two other events or time points, preserving their chronological order.
- 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27ca52cb881908c99913ea93bc88e |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:37 p.m.