Triple
T27187499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanjing Metro Line 10 |
E683377
|
entity |
| Predicate | connectsBankOfYangtze |
P73938
|
FINISHED |
| Object | north bank |
—
|
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: north bank | Statement: [Nanjing Metro Line 10, connectsBankOfYangtze, north bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsBankOfYangtze Context triple: [Nanjing Metro Line 10, connectsBankOfYangtze, north bank]
-
A.
connectsBank
Indicates a relationship where one entity serves to link or provide access between another entity and a bank or banking service.
-
B.
crossRiverLink
chosen
Indicates a connection or route that enables passage across a river between two locations.
-
C.
connectedToMainlandBy
Indicates that one landmass or area is physically linked to a mainland, typically via a bridge, causeway, or other continuous connection.
-
D.
linkedToRiver
Indicates a relationship where something is physically or functionally connected to, associated with, or dependent on a river.
-
E.
SeikanTunnelConnects
Indicates that the Seikan Tunnel serves as a physical connection between two geographic locations or regions.
- 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_69eefad140408190b8586fdebcf9af46 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 27, 2026, 9:31 a.m.