Triple
T22837145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leaning bell tower of San Martino |
E565977
|
entity |
| Predicate | hasCauseOfLean |
P708
|
FINISHED |
| Object | subsidence of foundations |
—
|
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: subsidence of foundations | Statement: [Leaning bell tower of San Martino, hasCauseOfLean, subsidence of foundations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCauseOfLean Context triple: [Leaning bell tower of San Martino, hasCauseOfLean, subsidence of foundations]
-
A.
hasCause
chosen
Indicates that one entity is the reason for, or brings about, the occurrence or existence of another entity or event.
-
B.
hasProposedCause
Indicates that one entity is suggested or hypothesized to be the cause or explanation for another entity or event.
-
C.
eligibleCause
Indicates that one entity qualifies as a valid or acceptable cause or reason for another entity or outcome.
-
D.
hasEtiology
Indicates that one entity is the cause, origin, or underlying reason for the occurrence or existence of another entity or condition.
-
E.
possibleCauseOf
Indicates that one entity is a potential, but not certain, cause or contributing factor to another entity or outcome.
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e303cec81909c5c118dc8c93354 |
completed | April 29, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69eed2d117088190acbfe130d84f8627 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:35 p.m.