Triple
T38103030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MTR Tuen Ma line |
E951435
|
entity |
| Predicate | partialOpeningYear |
P137349
|
FINISHED |
| Object | 2020 |
—
|
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: 2020 | Statement: [MTR Tuen Ma line, partialOpeningYear, 2020]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partialOpeningYear Context triple: [MTR Tuen Ma line, partialOpeningYear, 2020]
-
A.
structureOpeningYear
Indicates the calendar year in which a structure was first opened for use or public access.
-
B.
officialOpeningYear
Indicates the calendar year in which something was formally opened or inaugurated for official use.
-
C.
originalPlannedOpeningYear
Indicates the year that was initially scheduled or intended for something to open, before any delays or changes.
-
D.
softOpeningYear
chosen
Indicates the year in which an entity began limited or preliminary operations before its official full opening.
-
E.
approximateOpeningYear
Indicates the estimated or roughly determined year in which something (such as a facility, venue, or organization) began operating or opened.
- 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_69f76f065ed08190bdfb1b6d817f5b39 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd3d46d1f48190a1b20dd063224b7d |
completed | May 8, 2026, 1:32 a.m. |
| PD | Predicate disambiguation | batch_69fd3ae1510c81908fe1280efc17feee |
completed | May 8, 2026, 1:22 a.m. |
Created at: May 3, 2026, 4:21 p.m.