Triple
T12314665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TfL Rail |
E293569
|
entity |
| Predicate | startOfWestLondonOperations |
P81328
|
FINISHED |
| Object | 2018-05-20 |
—
|
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: 2018-05-20 | Statement: [TfL Rail, startOfWestLondonOperations, 2018-05-20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startOfWestLondonOperations Context triple: [TfL Rail, startOfWestLondonOperations, 2018-05-20]
-
A.
westEndOpeningDate
Indicates the calendar date on which a production or event first opened in London’s West End.
-
B.
operatorStartDate
chosen
Indicates the date on which an operator’s role, activity, or responsibility begins.
-
C.
HeathrowBranchOpeningDate
Indicates the date on which the Heathrow branch was officially opened.
-
D.
westEndOpeningYear
Indicates the calendar year in which something (typically a production or show) first opened in London’s West End.
-
E.
startTimeAsMPForLancasterAndWyre
Indicates the date and time at which an individual first began serving as Member of Parliament for the Lancaster and Wyre constituency.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.