Triple
T4101429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Theatre (Amman) |
E87948
|
entity |
| Predicate | designedToFace |
P53371
|
FINISHED |
| Object | north to avoid sun |
—
|
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: north to avoid sun | Statement: [Roman Theatre (Amman), designedToFace, north to avoid sun]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedToFace Context triple: [Roman Theatre (Amman), designedToFace, north to avoid sun]
-
A.
facedBy
Indicates that one entity is oriented toward and directly opposite another entity, such that it is facing it.
-
B.
isDesignedFor
Indicates that one entity has been created, planned, or optimized specifically to serve the needs, purposes, or use of another entity.
-
C.
faceType
Indicates the specific shape or structural category of a face that an entity possesses or is characterized by.
-
D.
designedWith
Indicates that one entity was created, planned, or developed using another entity as a tool, method, or guiding basis in its design process.
-
E.
leftFacingAssociatedWith
Indicates an association where one entity is oriented or positioned facing toward the left relative to another entity.
- 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0ed168819093c83ba079d6725c |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90b2ef08190ae84febfd69dd48b |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aefa5c52648190b001027f4dba75cb |
completed | March 9, 2026, 4:50 p.m. |
Created at: March 9, 2026, 3:40 p.m.