Triple
T27359485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keihan Uji Line |
E685778
|
entity |
| Predicate | secondaryPassengerBase |
P157172
|
FINISHED |
| Object | tourists |
—
|
LITERAL 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: tourists | Statement: [Keihan Uji Line, secondaryPassengerBase, tourists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryPassengerBase Context triple: [Keihan Uji Line, secondaryPassengerBase, tourists]
-
A.
secondaryPassengerProfile
Indicates that an entity serves as an additional or non-primary passenger associated with a main travel booking or passenger profile.
-
B.
primaryPassengerGroup
Indicates the main group of passengers that is most directly associated with or served by a given entity or context.
-
C.
passengers
Indicates that one entity is traveling in or being transported by another entity, typically as a non-operating occupant.
-
D.
secondPartySeats
Indicates that a second party assigns or provides seating or seats to another entity.
-
E.
hasSecondaryOccupant
chosen
Indicates that an entity has an additional, non-primary occupant associated with it.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.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: April 27, 2026, 11:53 a.m.