Triple
T27855718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haddenham and Thame Parkway |
E704077
|
entity |
| Predicate | hasBusLinkTo |
P132153
|
FINISHED |
| Object | Thame town centre |
—
|
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: Thame town centre | Statement: [Haddenham and Thame Parkway, hasBusLinkTo, Thame town centre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBusLinkTo Context triple: [Haddenham and Thame Parkway, hasBusLinkTo, Thame town centre]
-
A.
isTransportationLinkBetween
chosen
Indicates that there exists a transportation connection (such as a road, rail, air, or sea route) linking the two entities.
-
B.
hasBusServices
Indicates that one location or entity is served by bus routes or bus transportation provided by another.
-
C.
hasTransportationRelation
Indicates a relationship in which one entity provides, uses, is connected by, or is otherwise associated with a means or mode of transportation to another entity or location.
-
D.
hasBusLoop
Indicates that a location or facility includes a designated looped roadway or area specifically for bus circulation, stopping, or turning.
-
E.
hasBusOperator
Indicates that a bus service, route, or vehicle is operated or managed by a specific operator or company.
- 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_69ef840e614c8190a88cf9638c14a265 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 27, 2026, 6:14 p.m.