Triple
T10830541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luton railway station |
E255605
|
entity |
| Predicate | hasServiceTo |
P6787
|
FINISHED |
| Object | Three Bridges |
E424423
|
NE 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: Three Bridges | Statement: [Luton railway station, hasServiceTo, Three Bridges]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Three Bridges Context triple: [Luton railway station, hasServiceTo, Three Bridges]
-
A.
Three Bridges
chosen
Three Bridges is a residential and commercial neighbourhood in the town of Crawley in West Sussex, England.
-
B.
Bridges
Bridges is a common English surname borne by various notable individuals, including actors, politicians, and athletes.
-
C.
Bridges
Bridges is the fictional United Cities of America organization in the video game "Death Stranding," responsible for reconnecting isolated cities and managing porters like Sam Porter Bridges.
-
D.
Two Bridges
Two Bridges is a residential neighborhood on Manhattan’s Lower East Side, situated along the East River between the Manhattan and Brooklyn Bridges.
-
E.
Twin Bridges
Twin Bridges is a themed world in the video game Super Mario World, characterized by its pair of bridge-like areas and associated levels.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d744222288819093258b452569acab |
completed | April 9, 2026, 6:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de85a068b08190948c3ca32cdda147 |
completed | April 14, 2026, 6:21 p.m. |
Created at: April 8, 2026, 9:19 p.m.