Triple
T8887820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kansai Kūkō |
E211578
|
entity |
| Predicate | hasTerminal |
P182
|
FINISHED |
| Object |
Terminal 2
Terminal 2 is a low-cost carrier-focused passenger terminal at Kansai International Airport in Osaka, Japan.
|
E48198
|
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 2 | Statement: [Kansai Kūkō, hasTerminal, Terminal 2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal 2 Context triple: [Kansai Kūkō, hasTerminal, Terminal 2]
-
A.
Terminal 2
Terminal 2 is one of the main passenger terminals at Manchester Airport, handling a large share of the airport’s international and domestic flights.
-
B.
Terminal 2
Terminal 2 is a passenger terminal at El Dorado International Airport in Bogotá, Colombia, serving specific airlines and routes within the airport’s operations.
-
C.
Terminal 2
Terminal 2 is one of the main passenger terminals at Ontario International Airport in Southern California, serving domestic airline operations and traveler services.
-
D.
Terminal 2
Terminal 2 is one of the passenger terminals at Chicago O'Hare International Airport, serving various domestic and regional flights with multiple concourses and airline operations.
-
E.
Terminal 2
Terminal 2 is a secondary passenger terminal at Lisbon’s Humberto Delgado Airport, mainly serving low-cost and regional airlines.
- 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 2 Triple: [Kansai Kūkō, hasTerminal, Terminal 2]
Generated description
Terminal 2 is a low-cost carrier-focused passenger terminal at Kansai International Airport in Osaka, Japan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Terminal 2 Target entity description: Terminal 2 is a low-cost carrier-focused passenger terminal at Kansai International Airport in Osaka, Japan.
-
A.
Terminal 2
chosen
Terminal 2 is a low-cost carrier–focused passenger terminal at Kansai International Airport in Osaka, Japan.
-
B.
Terminal 2
Terminal 2 is a major passenger terminal at Incheon International Airport in South Korea, serving as a modern hub for several international airlines.
-
C.
Terminal 2
Terminal 2 is one of the main passenger terminals at Tokyo's Haneda Airport, serving primarily domestic flights with modern facilities and amenities.
-
D.
Terminal 2
Terminal 2 is a passenger terminal at Don Mueang International Airport in Bangkok, primarily serving low-cost and domestic airline operations.
-
E.
Terminal 2
Terminal 2 is a concourse at St. Louis Lambert International Airport primarily serving low-cost and international carriers.
- 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_69ca83907954819096d52a245b635841 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc618e58d08190be3ebcbe3701b1db |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab821e808190a918bf787cde54b6 |
completed | April 3, 2026, 11:58 a.m. |
| NEDg | Description generation | batch_69cfad8cb9cc81909d4df290c7411898 |
completed | April 3, 2026, 12:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfae0141b48190a443ae181a495bf6 |
completed | April 3, 2026, 12:09 p.m. |
Created at: March 30, 2026, 6:53 p.m.