Triple
T17101855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spynie Palace |
E414997
|
entity |
| Predicate | hasStairType |
P11048
|
FINISHED |
| Object | spiral stair in tower |
—
|
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: spiral stair in tower | Statement: [Spynie Palace, hasStairType, spiral stair in tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStairType Context triple: [Spynie Palace, hasStairType, spiral stair in tower]
-
A.
hasStaircaseType
chosen
Indicates the specific type or design classification of a staircase associated with an entity.
-
B.
hasStairFunction
Indicates that one entity serves as a stair-related functional feature (e.g., providing access via stairs) for another entity.
-
C.
hasStairway
Indicates that one entity includes or is connected to another entity by a stairway providing vertical access between levels.
-
D.
hasStairName
Indicates that a stairway is associated with a specific name or designation.
-
E.
hasStairsFacing
Indicates that one set of stairs is oriented toward or directly faces another object or direction.
- 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_69d886cfc8e88190b05ba466edd35591 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dc239a088190a776fe0f4361ffc7 |
completed | April 18, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69e35d6b1b988190a8d6b6fe78c35e59 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:35 a.m.