Triple
T26551371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 天神 |
E671685
|
entity |
| Predicate | 主な交通機関 |
P109225
|
FINISHED |
| Object | 西日本鉄道天神大牟田線 |
—
|
NE NERFINISHED |
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: 西日本鉄道天神大牟田線 | Statement: [天神, 主な交通機関, 西日本鉄道天神大牟田線]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 主な交通機関 Context triple: [天神, 主な交通機関, 西日本鉄道天神大牟田線]
-
A.
primaryTransports
chosen
Indicates that one entity serves as the main means or method of transporting or conveying another entity.
-
B.
hasMajorTransportationRole
Indicates that an entity plays a primary or significant role in providing or supporting transportation services or infrastructure.
-
C.
typeOfTransportInfrastructure
Indicates the specific category or kind of transport infrastructure associated with or used in a given context.
-
D.
handlesMostPassengerTrafficOf
Indicates that one entity is responsible for managing the largest share of passenger traffic associated with another entity, compared to all similar entities.
-
E.
primaryTransportFunction
Indicates the main mode or role by which something serves to move people, goods, or information from one place to another.
- F. None of above.
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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f614624c80819084f6febf57f86828 |
completed | May 2, 2026, 3:12 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:47 a.m.