Triple
T37428856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leaning Tower of Günzburg |
E930073
|
entity |
| Predicate | hasTilt |
P56968
|
FINISHED |
| Object | slight lean from vertical |
—
|
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: slight lean from vertical | Statement: [Leaning Tower of Günzburg, hasTilt, slight lean from vertical]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTilt Context triple: [Leaning Tower of Günzburg, hasTilt, slight lean from vertical]
-
A.
tiltingCapability
Indicates the ability of one entity to tilt or be tilted relative to another or to a reference orientation.
-
B.
tiltedRelativeTo
chosen
Indicates that one entity is oriented at an angle with respect to another, rather than being parallel or perpendicular.
-
C.
tiltingMechanism
Indicates a relationship where one entity serves as a mechanism that enables another entity to tilt or be tilted.
-
D.
hasTension
Indicates the presence of strain, stress, or conflict between entities in their relationship or interaction.
-
E.
hasVerticality
Indicates that one entity possesses or exhibits vertical orientation, alignment, or extent relative to another reference.
- 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_69f76ebf0f288190ba198a78341613b8 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe6c811bcc81908b1e1b1f8bcb071b |
completed | May 8, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69fe6c026d5481908b7a814dcf38c183 |
completed | May 8, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:16 p.m.