Triple
T38286621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bangkok public transport system |
E1022228
|
entity |
| Predicate | boatOperator |
P176504
|
FINISHED |
| Object | Chao Phraya Express Boat Company |
—
|
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: Chao Phraya Express Boat Company | Statement: [Bangkok public transport system, boatOperator, Chao Phraya Express Boat Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: boatOperator Context triple: [Bangkok public transport system, boatOperator, Chao Phraya Express Boat Company]
-
A.
boatRole
Indicates the specific function, duty, or position an entity has in relation to a boat within a given context.
-
B.
boatService
chosen
Indicates that one entity provides or operates a transportation service by boat for another entity or between locations.
-
C.
boatLaunch
Indicates the action or event of setting a boat into the water from land or a structure so it can begin operating or traveling.
-
D.
boatServiceFrom
Indicates that a boat transportation service operates starting from a specified location to one or more other locations.
-
E.
boatPower
Indicates a relationship where a boat is characterized by or associated with a specific power rating or propulsion strength.
- 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_69f76df190f081908d5aa02c8a9286d0 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fccbd826708190b5fab12c4236299a |
completed | May 7, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69fcc58838e08190b8fa54aa5c165f2d |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:30 p.m.