Triple
T18759501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holocaust Memorial (Nameless Library, Vienna) |
E458731
|
entity |
| Predicate | bookSpinesOrientation |
P133434
|
FINISHED |
| Object | turned inward |
—
|
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: turned inward | Statement: [Holocaust Memorial (Nameless Library, Vienna), bookSpinesOrientation, turned inward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bookSpinesOrientation Context triple: [Holocaust Memorial (Nameless Library, Vienna), bookSpinesOrientation, turned inward]
-
A.
styleOrientation
Indicates the general stylistic direction or aesthetic approach that characterizes how something is designed, presented, or expressed.
-
B.
hasPaperbackEdition
Indicates that one entity has a corresponding edition of itself that is published in paperback format.
-
C.
hasFrontispiece
Indicates that an item includes a frontispiece, i.e., an illustrative or decorative page placed at or near the front of a work.
-
D.
isbnType
Indicates the specific classification or format type associated with an ISBN identifier for a publication.
-
E.
book4Covers
Indicates that one entity is the front or outer covering (such as a dust jacket or protective layer) of a book.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e58d7db2f48190a4f1c5c9801fe180 |
completed | April 20, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69e48d0b7b708190877951b6e6cdcbc4 |
completed | April 19, 2026, 8:06 a.m. |
| PDg | Predicate description generation | batch_69e49a9bcc0c81908df3e513fd6762ff |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 11:52 a.m.