Triple
T27081622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiralty |
E685609
|
entity |
| Predicate | MTRLine |
P18378
|
FINISHED |
| Object | Tsuen Wan line |
—
|
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: Tsuen Wan line | Statement: [Admiralty, MTRLine, Tsuen Wan line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MTRLine Context triple: [Admiralty, MTRLine, Tsuen Wan line]
-
A.
cityRailNetwork
Indicates that there exists a rail-based public transportation system operating within and serving the specified city.
-
B.
subwayLine
chosen
Indicates that there is a subway line connection or service relationship between the referenced entities.
-
C.
lightRailNetwork
Indicates a relationship where an area, city, or region is served by or contains a light rail transit network.
-
D.
cityRailStyle
Indicates that something follows or embodies the characteristic style, design, or operational pattern associated with a city rail system.
-
E.
monorailLines
Indicates that there is a monorail transit line or system associated with, serving, or present in the referenced entity.
- 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_69ef14843b1481909d828b3d5a44550a |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f623417cfc81908943186b0b8c3e7b |
completed | May 2, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:35 a.m.