Triple
T34311005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanja-sama |
E880443
|
entity |
| Predicate | accessByLine |
P137521
|
FINISHED |
| Object | Tokyo Metro Ginza Line |
—
|
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: Tokyo Metro Ginza Line | Statement: [Sanja-sama, accessByLine, Tokyo Metro Ginza Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessByLine Context triple: [Sanja-sama, accessByLine, Tokyo Metro Ginza Line]
-
A.
accessibleForLine
chosen
Indicates that something (such as a resource, area, or facility) can be reached, used, or served by a particular line (e.g., a transport or service line).
-
B.
keyLine
Indicates that a line or segment serves as a primary or defining reference line within a structure, system, or representation.
-
C.
associatedLine
Indicates that one entity is linked or connected to a particular line (such as a line item, line of text, or line in a structure) with which it is contextually or functionally related.
-
D.
carriedByLine
Indicates that something (such as a service, signal, or connection) is transported or conveyed via a particular line or conduit.
-
E.
actionLine
Indicates a relationship where an action or event is represented, traced, or depicted along a line or linear path between entities.
- 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_69f349b8bb6c8190ad12a7957a574f04 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 1, 2026, 1:57 a.m.