Triple
T13823973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ZBAA |
E332203
|
entity |
| Predicate | hasTerminal |
P182
|
FINISHED |
| Object |
Terminal 3
Terminal 3 is a major passenger terminal at Beijing Capital International Airport, known for its large capacity and modern facilities.
|
E70865
|
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: Terminal 3 | Statement: [ZBAA, hasTerminal, Terminal 3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal 3 Context triple: [ZBAA, hasTerminal, Terminal 3]
-
A.
Terminal 3
Terminal 3 is one of the main passenger terminals at Phoenix Sky Harbor International Airport, serving as a hub for multiple domestic and some international flights with modernized facilities and amenities.
-
B.
Terminal 3
Terminal 3 is the main international passenger terminal at José Martí International Airport in Havana, Cuba, handling most long-haul and major airline operations.
-
C.
Terminal 3
Terminal 3 is one of the main passenger terminals at Fort Lauderdale–Hollywood International Airport, serving various domestic and international airline operations.
-
D.
Terminal 3
Terminal 3 is one of the main domestic passenger terminals at Melbourne Airport, serving several Australian airlines and routes.
-
E.
Terminal 3
Terminal 3 is a major domestic passenger terminal at San Francisco International Airport, primarily serving United Airlines and its partners.
- 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: Terminal 3 Triple: [ZBAA, hasTerminal, Terminal 3]
Generated description
Terminal 3 is a major passenger terminal at Beijing Capital International Airport, known for its large capacity and modern facilities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Terminal 3 Target entity description: Terminal 3 is a major passenger terminal at Beijing Capital International Airport, known for its large capacity and modern facilities.
-
A.
Terminal 3
chosen
Terminal 3 is the largest and most modern passenger terminal at Beijing Capital International Airport, serving as a major international aviation hub.
-
B.
Terminal 3
Terminal 3 is one of the main passenger terminals at London Heathrow Airport, serving numerous international airlines and long-haul flights.
-
C.
Terminal 3
Terminal 3 is a major passenger terminal at an airport, typically serving as a hub for numerous domestic and international flights with extensive check-in, security, and boarding facilities.
-
D.
Terminal 3
Terminal 3 is a major passenger terminal at Dubai International Airport, primarily serving Emirates and known as one of the largest airport terminals in the world.
-
E.
Terminal 3
Terminal 3 is a major passenger terminal at Wuhan Tianhe International Airport, serving as a key hub for domestic and international air travel in central China.
- F. None of above.
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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0285fb7c8190be4b90bdc0d6fa53 |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8e85c6c81908bdf5d43b917d151 |
completed | May 3, 2026, 9:06 p.m. |
| NEDg | Description generation | batch_69f7b9d81f488190875e9b3f885556ab |
completed | May 3, 2026, 9:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7ba99ad9c8190906b6b63cf27a446 |
completed | May 3, 2026, 9:14 p.m. |
Created at: April 9, 2026, 10:13 p.m.