Triple
T21186462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garisenda Tower |
E522091
|
entity |
| Predicate | structuralModification |
P43320
|
FINISHED |
| Object | reduced in height in the Middle Ages for safety reasons |
—
|
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: reduced in height in the Middle Ages for safety reasons | Statement: [Garisenda Tower, structuralModification, reduced in height in the Middle Ages for safety reasons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: structuralModification Context triple: [Garisenda Tower, structuralModification, reduced in height in the Middle Ages for safety reasons]
-
A.
modification
chosen
Indicates a change made to an existing entity, altering its properties, structure, or state from a prior version.
-
B.
leafModification
Indicates a relationship where an entity undergoes or causes a change in the structure, form, or characteristics of a leaf.
-
C.
laterModification
Indicates that one entity is a modification or revision that occurs after another in time.
-
D.
modifiesMorphologyOf
Indicates that one entity alters or changes the morphological structure or form of another entity.
-
E.
revisionMechanism
Indicates the method or process by which something is updated, corrected, or modified over time.
- 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_69e0b50ef1d48190b063aa342667df22 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7302222788190aa55ee0ed7342498 |
completed | April 21, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69e5f6027c248190a170a36612bd337e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:07 p.m.