Triple
T22961693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ponte Santa Trinita |
E570915
|
entity |
| Predicate | hasSpanShape |
P122834
|
FINISHED |
| Object | elliptical arch |
—
|
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: elliptical arch | Statement: [Ponte Santa Trinita, hasSpanShape, elliptical arch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpanShape Context triple: [Ponte Santa Trinita, hasSpanShape, elliptical arch]
-
A.
isSpanning
Indicates that one entity extends across, covers, or bridges the full width, extent, or duration of another entity.
-
B.
hasMainSpanLength
Indicates the relationship specifying the primary or main span’s length associated with an entity.
-
C.
hasNavigationSpan
Indicates that one entity includes or is associated with a specific navigational range or segment used for movement or routing.
-
D.
hasSectionShape
chosen
Indicates that one entity possesses or is characterized by a particular cross-sectional shape specified by another entity.
-
E.
hasMovableSpan
Indicates that an object or structure includes a span or section that can be moved or repositioned rather than being fixed in place.
- 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f494348190a24f09d3495b0950 |
completed | April 29, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9101f48190a06c69dff26c6441 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:47 p.m.