Triple
T8517767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Shentong Metro Group |
E201617
|
entity |
| Predicate | networkTypeManaged |
P3937
|
FINISHED |
| Object | urban rapid transit |
—
|
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: urban rapid transit | Statement: [Shanghai Shentong Metro Group, networkTypeManaged, urban rapid transit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkTypeManaged Context triple: [Shanghai Shentong Metro Group, networkTypeManaged, urban rapid transit]
-
A.
isPartOfNetworkManagedBy
Indicates that an entity belongs to and operates under the control or administration of a specific network management authority or system.
-
B.
networkType
chosen
Indicates the category or kind of network associated with or used by an entity (e.g., wired, wireless, virtual, or specific protocol-based networks).
-
C.
internetDomainTypeManaged
Indicates that the internet domain is administered or controlled by a managing authority or organization.
-
D.
modeManaged
Indicates that one entity controls, configures, or oversees the operational mode or state of another entity.
-
E.
classificationTypeManaged
Indicates that the classification type is controlled or administered through a managed process or system rather than being assigned freely or ad hoc.
- 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe626787c819087e72dd76b2d9310 |
completed | March 31, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_69cbd10f64b4819080859057c19e58f0 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:15 p.m.