Triple
T10460164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Airport Express |
E246649
|
entity |
| Predicate | averageJourneyTime |
P46906
|
FINISHED |
| Object | about 24 minutes between Hong Kong and Airport |
—
|
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: about 24 minutes between Hong Kong and Airport | Statement: [Airport Express, averageJourneyTime, about 24 minutes between Hong Kong and Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageJourneyTime Context triple: [Airport Express, averageJourneyTime, about 24 minutes between Hong Kong and Airport]
-
A.
travelTimeTypical
chosen
Indicates the usual or expected amount of time it takes to travel between two locations under normal conditions.
-
B.
transitFrequencyApprox
Indicates an approximate rate or regularity with which a transit event or service occurs between entities.
-
C.
travelTimeByFerry
Indicates the duration required to travel between two locations specifically using a ferry as the mode of transportation.
-
D.
travelTimeCategory
Indicates the qualitative classification of how long a given travel or trip duration is (e.g., short, medium, long).
-
E.
previousTravelTimeOnRoute
Indicates the duration of travel that occurred earlier on the same route before the current segment or time period.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50882eb0c8190a4311634b867eab1 |
completed | April 7, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69d4fb7d353c8190a73f439a956c7606 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:18 p.m.