Triple
T32757202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Still Life before an Open Window, Place Ravignan |
E837660
|
entity |
| Predicate | titleLocation |
P148434
|
FINISHED |
| Object | Place Ravignan |
—
|
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: Place Ravignan | Statement: [Still Life before an Open Window, Place Ravignan, titleLocation, Place Ravignan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleLocation Context triple: [Still Life before an Open Window, Place Ravignan, titleLocation, Place Ravignan]
-
A.
associatedTitleLocation
chosen
Indicates a relationship where a title is linked to a specific location with which it is contextually or formally connected.
-
B.
textLocation
Indicates the spatial or positional relationship of a piece of text within a larger document, page, or layout.
-
C.
subjectLocation
Indicates that one entity is located at, in, or near the place or position specified by another entity.
-
D.
labelLocation
Indicates that a label or identifier is associated with a specific spatial or geographic location.
-
E.
headLocation
Indicates the spatial position or place where an entity’s head is located.
- 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_69f34937f97c8190b7f84bea045df3ae |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69feced53a7c819098ec474fb7d514b0 |
completed | May 9, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69fecd9cd5288190aac8b4e04a7ee78e |
completed | May 9, 2026, 6:01 a.m. |
Created at: May 1, 2026, 1:13 a.m.