Triple
T12300221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oni Synagogue |
E293198
|
entity |
| Predicate | facingDirectionOfAronKodesh |
P73279
|
FINISHED |
| Object | east |
—
|
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: east | Statement: [Oni Synagogue, facingDirectionOfAronKodesh, east]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: facingDirectionOfAronKodesh Context triple: [Oni Synagogue, facingDirectionOfAronKodesh, east]
-
A.
gateOrientation
Indicates the directional alignment or facing direction of a gate relative to a reference frame or coordinate system.
-
B.
directionRelativeTo
chosen
Indicates the spatial orientation of one entity in relation to another, such as which way it faces or points relative to a reference entity.
-
C.
offsetDirection
Indicates the relative direction in which one entity is displaced or shifted from another reference entity.
-
D.
directionalDesignation
Indicates a relationship where one entity is assigned or labeled with a specific directional orientation relative to another entity or reference frame.
-
E.
directionOfAppearance
Indicates the spatial direction or orientation from which something becomes visible or appears relative to a reference point or observer.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.