Triple
T17634204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Parnassus |
E430050
|
entity |
| Predicate | positionWithinRoom |
P63244
|
FINISHED |
| Object | wall opposite The School of Athens |
—
|
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: wall opposite The School of Athens | Statement: [The Parnassus, positionWithinRoom, wall opposite The School of Athens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionWithinRoom Context triple: [The Parnassus, positionWithinRoom, wall opposite The School of Athens]
-
A.
positionInChamber
Indicates the specific location or role an entity holds within a particular chamber or assembly.
-
B.
positionOnCeiling
Indicates that one entity is located on or attached to the ceiling surface of another entity or space.
-
C.
positionWithinCastle
Indicates that one entity is located inside the spatial boundaries of a castle.
-
D.
positionWithinOz
Indicates that one entity’s location is situated inside or within the spatial boundaries of another entity referred to as “Oz.”
-
E.
positionOnEnvironment
chosen
Indicates the spatial placement or location of an entity relative to a surrounding environment or surface.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46ddea4688190a76a4225f268c0ac |
completed | April 19, 2026, 5:53 a.m. |
| PD | Predicate disambiguation | batch_69e3cddc87188190ac2f049b86038676 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 5:52 a.m.