Triple
T12229657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central–Mid-Levels Escalator |
E291440
|
entity |
| Predicate | directionSchedule |
P76663
|
FINISHED |
| Object | downwards in the morning |
—
|
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: downwards in the morning | Statement: [Central–Mid-Levels Escalator, directionSchedule, downwards in the morning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionSchedule Context triple: [Central–Mid-Levels Escalator, directionSchedule, downwards in the morning]
-
A.
transportDirection
Indicates the directional flow or route along which something is transported from an origin toward a destination.
-
B.
routeDirectionB
Indicates that one entity represents the direction or orientation of a route or path relative to another entity.
-
C.
routePlan
Indicates a planned path or sequence of steps for traveling from a starting point to a destination.
-
D.
routeDirectionA
chosen
Indicates the primary or first directional orientation or heading associated with a specific route.
-
E.
routeBetween
Indicates that there exists a path or connection enabling travel or communication between two locations or points.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d924a3973c8190a882046963b320fb |
completed | April 10, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69d91c41bcbc81909782f4e3c571b218 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.