Triple
T8197761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Staro-Kalinkin Bridge |
E191475
|
entity |
| Predicate | reconstructedAsStoneBridge |
P45011
|
FINISHED |
| Object | late 18th century |
—
|
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: late 18th century | Statement: [Staro-Kalinkin Bridge, reconstructedAsStoneBridge, late 18th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reconstructedAsStoneBridge Context triple: [Staro-Kalinkin Bridge, reconstructedAsStoneBridge, late 18th century]
-
A.
rebuiltAsLiftBridge
Indicates that an existing structure was reconstructed or converted into a lift bridge.
-
B.
rebuiltInStone
chosen
Indicates that a previously existing structure was reconstructed using stone as the primary building material.
-
C.
reconstructedAs
Indicates that one entity has been rebuilt, recreated, or inferred based on evidence, models, or partial information from another entity.
-
D.
originalBridgeDestroyed
Indicates that the initially existing bridge in a given context has been destroyed.
-
E.
reconstructionBuilt
Indicates that one entity carried out or was responsible for constructing a rebuilt or restored version of another entity.
- 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_69ca82c6e9548190a4c5ca14516e4417 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb5c2341f881908be59c378896e5bc |
completed | March 31, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69cb36aac86081909b83636e352e0ced |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:42 p.m.