Triple
T4060004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apadana Palace |
E86186
|
entity |
| Predicate | entranceStairwaysLocation |
P1974
|
FINISHED |
| Object | north |
—
|
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 | Statement: [Apadana Palace, entranceStairwaysLocation, north]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: entranceStairwaysLocation Context triple: [Apadana Palace, entranceStairwaysLocation, north]
-
A.
hasStairway
Indicates that one entity includes or is connected to another entity by a stairway providing vertical access between levels.
-
B.
hasStairsFacing
Indicates that one set of stairs is oriented toward or directly faces another object or direction.
-
C.
hasEntranceOn
chosen
Indicates that one entity’s entrance or access point is located on or faces a specified side, boundary, or feature of another entity.
-
D.
hasEntranceStructure
Indicates that one entity possesses or is associated with a specific physical structure that serves as its entrance.
-
E.
hasLandmarkAtEntrance
Indicates that a specific landmark is located at or directly adjacent to the entrance of something.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.