Triple
T25879449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianjin Metro Line 10 |
E652005
|
entity |
| Predicate | urbanRailSystem |
P115324
|
FINISHED |
| Object | Tianjin Metro |
—
|
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: Tianjin Metro | Statement: [Tianjin Metro Line 10, urbanRailSystem, Tianjin Metro]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: urbanRailSystem Context triple: [Tianjin Metro Line 10, urbanRailSystem, Tianjin Metro]
-
A.
urbanRailHubFor
Indicates that a location functions as a central node or interchange point within an urban rail network for a given area or set of lines.
-
B.
urbanRailCategory
Indicates the classification of an urban rail system according to its type or category (e.g., metro, tram, light rail).
-
C.
cityRailNetwork
chosen
Indicates that there exists a rail-based public transportation system operating within and serving the specified city.
-
D.
rapidTransitSystem
Indicates a transportation relationship where people or goods are moved via a high-capacity, high-frequency public transit system designed for rapid travel over urban or regional routes.
-
E.
lightRailNetwork
Indicates a relationship where an area, city, or region is served by or contains a light rail transit network.
- 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_69e7ab3ad9d88190841ddcb93ab02e96 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6033d54948190a52da9e6bef00afa |
completed | May 2, 2026, 1:59 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 22, 2026, 8:13 a.m.