Triple
T15765357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 中部国際空港 |
E382205
|
entity |
| Predicate | hasPassengerTerminal |
P1297
|
FINISHED |
| Object |
第2ターミナル
第2ターミナルは、中部国際空港において主にLCCなどが利用するサテライト型の旅客ターミナルビルです。
|
E1176255
|
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: 第2ターミナル | Statement: [中部国際空港, hasPassengerTerminal, 第2ターミナル]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 第2ターミナル Context triple: [中部国際空港, hasPassengerTerminal, 第2ターミナル]
-
A.
Terminal 1
Terminal 1 is one of the main passenger terminals at Daniel K. Inouye International Airport in Honolulu, serving a large share of the airport’s domestic and inter-island flights.
-
B.
Terminal 1
Terminal 1 is a domestic passenger terminal at Chhatrapati Shivaji Maharaj International Airport in Mumbai, India.
-
C.
Terminal 1
Terminal 1 is the main passenger terminal at Don Mueang International Airport in Bangkok, handling a large share of the airport’s commercial flight operations.
-
D.
Terminal 1
Terminal 1 is one of the passenger terminals at Málaga Airport in Spain, serving as a facility for check-in, arrivals, and departures.
-
E.
Terminal 1
Terminal 1 is a major passenger terminal at Minneapolis–Saint Paul International Airport, historically known as the Lindbergh Terminal.
- 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: 第2ターミナル Triple: [中部国際空港, hasPassengerTerminal, 第2ターミナル]
Generated description
第2ターミナルは、中部国際空港において主にLCCなどが利用するサテライト型の旅客ターミナルビルです。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 第2ターミナル Target entity description: 第2ターミナルは、中部国際空港において主にLCCなどが利用するサテライト型の旅客ターミナルビルです。
-
A.
Terminal 1
Terminal 1 is a major passenger terminal at Guangzhou Baiyun International Airport, serving as one of the airport’s primary hubs for domestic and international flights.
-
B.
Terminal 1
Terminal 1 is one of the main passenger terminals at Daniel K. Inouye International Airport in Honolulu, serving a large share of the airport’s domestic and inter-island flights.
-
C.
Terminal 1
Terminal 1 is the main passenger terminal at Don Mueang International Airport in Bangkok, handling a large share of the airport’s commercial flight operations.
-
D.
Terminal 1
Terminal 1 is one of the main passenger terminals at Hazrat Shahjalal International Airport in Dhaka, Bangladesh, handling a significant share of the airport’s flight and traveler operations.
-
E.
Terminal 1
Terminal 1 is a major passenger terminal at Minneapolis–Saint Paul International Airport, historically known as the Lindbergh Terminal.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e050b8154881908afe5191e6424f15 |
completed | April 16, 2026, 3 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff9099335c8190b6f0fb336b3dc212 |
completed | May 9, 2026, 7:52 p.m. |
| NEDg | Description generation | batch_69ff93463d348190bd2c4cbd58bb2154 |
completed | May 9, 2026, 8:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff93b6321c8190baaee806dca1f73c |
completed | May 9, 2026, 8:06 p.m. |
Created at: April 10, 2026, 4:47 a.m.