Triple
T24645909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matadi Bridge |
E610108
|
entity |
| Predicate | approachStructureType |
P157155
|
FINISHED |
| Object | viaducts |
—
|
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: viaducts | Statement: [Matadi Bridge, approachStructureType, viaducts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approachStructureType Context triple: [Matadi Bridge, approachStructureType, viaducts]
-
A.
originalStructureType
Indicates the type or category of the structure that an entity originally had before any changes or transformations.
-
B.
hasApproachStructure
Indicates that one entity possesses or includes an approach structure that provides access or a path leading to another entity.
-
C.
designedStructureType
Indicates the type or category of structure that something has been specifically designed to be.
-
D.
laterStructureType
Indicates that one structure is of a type that occurs or is instantiated later than another structure in a temporal or sequential sense.
-
E.
hasStructureType
Indicates that an entity possesses or is classified by a specific structural type or configuration.
- F. None of above. chosen
Provenance (4 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_69e2c4d350a481909170482bc2ce6af9 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f422aee0408190899efe7e24ef2b40 |
completed | May 1, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f420e92cc88190a803aecdae78a051 |
completed | May 1, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f422add8508190a76e56cfa756eeb8 |
completed | May 1, 2026, 3:49 a.m. |
Created at: April 18, 2026, 2:33 a.m.