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.