Triple
T37415755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Buses route N381 |
E929701
|
entity |
| Predicate | replacesServiceWhen |
P197311
|
FINISHED |
| Object | many daytime routes are not running |
—
|
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: many daytime routes are not running | Statement: [London Buses route N381, replacesServiceWhen, many daytime routes are not running]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacesServiceWhen Context triple: [London Buses route N381, replacesServiceWhen, many daytime routes are not running]
-
A.
replacesSystemInServiceSince
Indicates that one system takes over the role or function of another system that has been in service since a specified time.
-
B.
enteredServiceAsReplacementFor
Indicates that one entity began its period of service specifically to take over the role or function previously performed by another entity.
-
C.
replacesSupportFor
Indicates that one entity takes over or substitutes for the role or function previously provided by another entity’s support.
-
D.
replacesSeries
Indicates that one series succeeds and takes the place of another series, typically as its official continuation or substitute.
-
E.
serviceRenamedAs
Indicates that a service previously known by one name is now identified or referred to by a different name.
- F. None of above. chosen
Provenance (4 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_69f76ebde49481908566cd96b37ccc84 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe86cad5108190b0164b8bc6fc23ea |
completed | May 9, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69fe83c0c9888190b6fc40c7f727b569 |
completed | May 9, 2026, 12:45 a.m. |
| PDg | Predicate description generation | batch_69fe86c98d688190a99d5dcb14e2dc95 |
completed | May 9, 2026, 12:58 a.m. |
Created at: May 3, 2026, 4:16 p.m.