Triple
T8174378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NRT |
E190904
|
entity |
| Predicate | railServicesInclude |
P21523
|
FINISHED |
| Object | Keisei Skyliner |
E235302
|
NE FINISHED |
How this triple was built (2 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: Keisei Skyliner | Statement: [NRT, railServicesInclude, Keisei Skyliner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keisei Skyliner Context triple: [NRT, railServicesInclude, Keisei Skyliner]
-
A.
Keisei Skyliner
chosen
Keisei Skyliner is a high-speed limited express train service in Japan that links central Tokyo with Narita International Airport.
-
B.
Rokkō Liner
Rokkō Liner is an automated guideway transit line in Kobe, Japan, connecting the artificial island of Rokkō Island with the mainland.
-
C.
Narita Express
Narita Express is a limited express train service in Japan that provides fast, direct rail connections between central Tokyo and Narita International Airport.
-
D.
Tsukuba Express
Tsukuba Express is a high-speed commuter railway line in Japan connecting central Tokyo with the city of Tsukuba in Ibaraki Prefecture.
-
E.
Haruka limited express
Haruka limited express is a Japanese limited express train service connecting Kansai International Airport with major destinations such as Kyoto and Osaka, primarily serving airport travelers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb7266bc148190984060b7b95effb5 |
completed | March 31, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd94bbdc288190aee5187e95ca7a8d |
completed | April 1, 2026, 9:57 p.m. |
Created at: March 30, 2026, 5:40 p.m.