Triple
T13903678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing Zoo |
E334290
|
entity |
| Predicate | publicTransitStop |
P6657
|
FINISHED |
| Object |
Beijing Zoo Station
Beijing Zoo Station is a subway station in Beijing that serves the area around the Beijing Zoo and connects it to the city's public transit network.
|
E1148211
|
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: Beijing Zoo Station | Statement: [Beijing Zoo, publicTransitStop, Beijing Zoo Station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beijing Zoo Station Context triple: [Beijing Zoo, publicTransitStop, Beijing Zoo Station]
-
A.
Beigongmen station
Beigongmen station is a subway station on the Beijing Subway network serving the area near the Summer Palace in Beijing.
-
B.
Lujiazui station
Lujiazui station is a major Shanghai Metro stop serving the city’s key financial district in Pudong.
-
C.
Baliqiao Station
Baliqiao Station is a stop on Beijing’s Batong Line, serving passengers in the eastern part of the city’s subway network.
-
D.
Chongwenmen station
Chongwenmen station is a major interchange stop on the Beijing Subway serving central Beijing near the historic Chongwenmen gate area.
-
E.
Hepingmen station
Hepingmen station is an underground metro station on the Beijing Subway serving the central Xicheng District near historic commercial and cultural areas.
- 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: Beijing Zoo Station Triple: [Beijing Zoo, publicTransitStop, Beijing Zoo Station]
Generated description
Beijing Zoo Station is a subway station in Beijing that serves the area around the Beijing Zoo and connects it to the city's public transit network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Beijing Zoo Station Target entity description: Beijing Zoo Station is a subway station in Beijing that serves the area around the Beijing Zoo and connects it to the city's public transit network.
-
A.
Beigongmen station
Beigongmen station is a subway station on the Beijing Subway network serving the area near the Summer Palace in Beijing.
-
B.
Lujiazui station
Lujiazui station is a major Shanghai Metro stop serving the city’s key financial district in Pudong.
-
C.
Baliqiao Station
Baliqiao Station is a stop on Beijing’s Batong Line, serving passengers in the eastern part of the city’s subway network.
-
D.
Chongwenmen station
Chongwenmen station is a major interchange stop on the Beijing Subway serving central Beijing near the historic Chongwenmen gate area.
-
E.
Hepingmen station
Hepingmen station is an underground metro station on the Beijing Subway serving the central Xicheng District near historic commercial and cultural 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25db1e308190aaed6a21e443cc44 |
completed | April 14, 2026, 11:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feef5c11708190a7fd4c0682b6ed81 |
completed | May 9, 2026, 8:25 a.m. |
| NEDg | Description generation | batch_69fef09f396481908c081a41a5e35cd3 |
completed | May 9, 2026, 8:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fef133d310819087424d794dae0074 |
completed | May 9, 2026, 8:32 a.m. |
Created at: April 9, 2026, 10:16 p.m.