Triple
T7384715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanjing Metro |
E170351
|
entity |
| Predicate | hasLine |
P35
|
FINISHED |
| Object |
Line 3
Line 3 is a rapid transit route of the Nanjing Metro system in Nanjing, China, serving as one of the city's main north–south subway lines.
|
E660751
|
NE FINISHED |
How this triple was built (4 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: Line 3 | Statement: [Nanjing Metro, hasLine, Line 3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Line 3 Context triple: [Nanjing Metro, hasLine, Line 3]
-
A.
Line 3
Line 3 is a route of Mexico City’s Metrobús bus rapid transit system that serves key corridors with dedicated lanes and high-capacity articulated buses.
-
B.
Line 3
Line 3 is a rapid transit line of the Toronto subway system, commonly known as the Scarborough RT, that served the Scarborough district.
-
C.
Line 3
Line 3 is a major north–south route of the Seoul Metropolitan Subway system, connecting key residential and commercial districts across the city and into surrounding areas.
-
D.
Line 3
Line 3 is a major rapid transit route of the STC Metro system, serving key districts along its corridor.
-
E.
Line 3
Line 3 is a major line of the Saint Petersburg Metro system, serving as one of the city's primary rapid transit routes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Line 3 Triple: [Nanjing Metro, hasLine, Line 3]
Generated description
Line 3 is a rapid transit route of the Nanjing Metro system in Nanjing, China, serving as one of the city's main north–south subway lines.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Line 3 Target entity description: Line 3 is a rapid transit route of the Nanjing Metro system in Nanjing, China, serving as one of the city's main north–south subway lines.
-
A.
Line 3
Line 3 is a major north–south rapid transit route of the Shanghai Metro system, known for its elevated tracks and extensive coverage across the city.
-
B.
Line 3
Line 3 is a rapid transit line of the Shenzhen Metro system in Shenzhen, China, serving key urban districts along a major north–south corridor.
-
C.
Line 3
Line 3 is one of the main lines of the Mexico City Metro system, running in a generally north–south direction and serving several key residential and commercial areas.
-
D.
Line 3
Line 3 is a major rapid transit route of the STC Metro system, serving key districts along its corridor.
-
E.
Line 3
Line 3 is a major north–south route of the Seoul Metropolitan Subway system, connecting key residential and commercial districts across the city and into surrounding areas.
- F. None of above. chosen
Provenance (5 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_69c68a5d0ed08190b6d361e68f813330 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1efe1308190b96eefbff56140be |
completed | March 27, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802e23714819094a1b31c82a27fee |
completed | March 28, 2026, 4:33 p.m. |
| NEDg | Description generation | batch_69c8038127408190947cb7002ccc0dec |
completed | March 28, 2026, 4:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8040a40088190b37192429678fd3e |
completed | March 28, 2026, 4:38 p.m. |
Created at: March 27, 2026, 3:08 p.m.