Triple
T27353247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tramways Hong Kong Island line |
E685617
|
entity |
| Predicate | isCommuterService |
P165385
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Tramways Hong Kong Island line, isCommuterService, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCommuterService Context triple: [Tramways Hong Kong Island line, isCommuterService, true]
-
A.
hasCommuterServices
Indicates that a location or facility provides transportation services specifically intended for regular commuters, such as daily or frequent travelers between home and work or school.
-
B.
isCommuterHub
Indicates that a location functions as a central node where many commuters start, end, or transfer during their regular travel.
-
C.
hasCommuterOperator
Indicates that an entity (such as a route, service, or station) is operated or served by a specific commuter transport operator.
-
D.
operatesCommuterServiceBetween
Indicates that an entity runs a commuter transportation service connecting two specified locations.
-
E.
commuterServiceTo
Indicates a transportation service that regularly carries commuters to a specified destination.
- F. None of above. chosen
Provenance (4 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_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 27, 2026, 11:49 a.m.