Triple
T35839699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Datong–Xi’an passenger-dedicated railway |
E1036041
|
entity |
| Predicate | startPointProvince |
P79461
|
FINISHED |
| Object | Shanxi Province |
—
|
NE NERFINISHED |
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: Shanxi Province | Statement: [Datong–Xi’an passenger-dedicated railway, startPointProvince, Shanxi Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startPointProvince Context triple: [Datong–Xi’an passenger-dedicated railway, startPointProvince, Shanxi Province]
-
A.
baseProvince
chosen
Indicates that one administrative or territorial unit serves as the primary or originating province associated with another entity.
-
B.
destinationProvince
Indicates the province that serves as the endpoint or target location of a movement, transfer, or route.
-
C.
endProvince
Indicates that an entity marks the boundary or final extent of a province within a larger territorial or administrative structure.
-
D.
startPointIsCapitalOf
Indicates that the starting point in a relation or path is a city that serves as the capital of the relevant region, country, or administrative entity.
-
E.
startPoint
Indicates the initial location or position from which an object, path, or action begins.
- 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_69f76e1a29e8819088280f26096aeb55 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a008ac37dc081908d360574912f40ec |
completed | May 10, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_6a008a67d73881909855ab4cfca3c399 |
completed | May 10, 2026, 1:38 p.m. |
Created at: May 3, 2026, 4:06 p.m.