Triple
T9336344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leaning Tower of Toruń |
E224651
|
entity |
| Predicate | causeOfTilt |
P694
|
FINISHED |
| Object | unstable sandy ground |
—
|
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: unstable sandy ground | Statement: [Leaning Tower of Toruń, causeOfTilt, unstable sandy ground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfTilt Context triple: [Leaning Tower of Toruń, causeOfTilt, unstable sandy ground]
-
A.
tiltingMechanism
Indicates a relationship where one entity serves as a mechanism that enables another entity to tilt or be tilted.
-
B.
tiltingCapability
Indicates the ability of one entity to tilt or be tilted relative to another or to a reference orientation.
-
C.
causeOf
chosen
Indicates that one entity brings about, produces, or is responsible for the occurrence or existence of another entity or event.
-
D.
tiltedRelativeTo
Indicates that one entity is oriented at an angle with respect to another, rather than being parallel or perpendicular.
-
E.
fallCause
Indicates that one event or condition causes or brings about another event of falling or decline.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37f161e481908e23c1ec7e5fcf97 |
completed | April 1, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:40 p.m.