Triple
T8363183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 3 |
E197059
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object |
Narita City
Narita City is a Japanese city in Chiba Prefecture best known internationally as the location of Narita International Airport, one of the main gateways to Tokyo.
|
E761465
|
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: Narita City | Statement: [Terminal 3, locatedIn, Narita City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Narita City Context triple: [Terminal 3, locatedIn, Narita City]
-
A.
Yokohama
Yokohama is Japan’s second-largest city and a major international port located just south of Tokyo.
-
B.
Fuji City
Fuji City is an industrial city in Shizuoka Prefecture, Japan, known for its paper manufacturing industry and views of nearby Mount Fuji.
-
C.
Akishima
Akishima is a city in western Tokyo, Japan, known as part of the Tama area and characterized by its residential neighborhoods and light industry.
-
D.
Bunkyō City
Bunkyō City is a special ward in central Tokyo, Japan, known for its universities, historic temples, and quiet residential neighborhoods.
-
E.
Hachiōji
Hachiōji is a city in western Tokyo, Japan, known as a regional commercial and educational hub with rich historical sites and access to nearby mountains and nature.
- 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: Narita City Triple: [Terminal 3, locatedIn, Narita City]
Generated description
Narita City is a Japanese city in Chiba Prefecture best known internationally as the location of Narita International Airport, one of the main gateways to Tokyo.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Narita City Target entity description: Narita City is a Japanese city in Chiba Prefecture best known internationally as the location of Narita International Airport, one of the main gateways to Tokyo.
-
A.
Yokohama
Yokohama is Japan’s second-largest city and a major international port located just south of Tokyo.
-
B.
Fuji City
Fuji City is an industrial city in Shizuoka Prefecture, Japan, known for its paper manufacturing industry and views of nearby Mount Fuji.
-
C.
Akishima
Akishima is a city in western Tokyo, Japan, known as part of the Tama area and characterized by its residential neighborhoods and light industry.
-
D.
Bunkyō City
Bunkyō City is a special ward in central Tokyo, Japan, known for its universities, historic temples, and quiet residential neighborhoods.
-
E.
Hachiōji
Hachiōji is a city in western Tokyo, Japan, known as a regional commercial and educational hub with rich historical sites and access to nearby mountains and nature.
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80768b208190a5f6c9e6cb6e7f30 |
completed | March 31, 2026, 8:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf887208188190902ad8be01397371 |
completed | April 3, 2026, 9:29 a.m. |
| NEDg | Description generation | batch_69cf8c85e154819098b446ac0acac880 |
completed | April 3, 2026, 9:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cf8cda73588190b1fe48ba512d302d |
completed | April 3, 2026, 9:48 a.m. |
Created at: March 30, 2026, 6 p.m.