Triple
T35362636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perlis (ferry terminal town) |
E1021534
|
entity |
| Predicate | servesFerryRouteTo |
P1737
|
FINISHED |
| Object | Langkawi |
—
|
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: Langkawi | Statement: [Perlis (ferry terminal town), servesFerryRouteTo, Langkawi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesFerryRouteTo Context triple: [Perlis (ferry terminal town), servesFerryRouteTo, Langkawi]
-
A.
ferryRouteName
Indicates the specific name assigned to a ferry route that connects two or more locations.
-
B.
hasFerryService
chosen
Indicates that there is an operational ferry connection or transport service available between the related locations or entities.
-
C.
isOneOfMainCarFerryRoutesTo
Indicates that something serves as one of the primary car ferry routes leading to a specified destination.
-
D.
hasNearbyFerryRoute
Indicates that there is a ferry route located close to the referenced entity.
-
E.
ferryServiceName
Indicates the specific name assigned to a ferry service operating between locations.
- 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_69f76def44c881908a20e8008572eb44 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fffc783b648190bcd7df017514d206 |
completed | May 10, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69fffc03fa24819099e12413dc6e0afd |
completed | May 10, 2026, 3:31 a.m. |
Created at: May 3, 2026, 4:03 p.m.