Triple
T10830579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luton Town Hall |
E255606
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Luton town centre |
E51115
|
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: Luton town centre | Statement: [Luton Town Hall, locatedIn, Luton town centre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luton town centre Context triple: [Luton Town Hall, locatedIn, Luton town centre]
-
A.
Luton
chosen
Luton is a large town in Bedfordshire, England, known for its international airport and diverse urban population.
-
B.
The Mall Luton
The Mall Luton is a major shopping centre in Luton, England, featuring a wide range of retail stores, eateries, and services.
-
C.
Luton, Chatham
Luton is a residential suburb and neighbourhood of Chatham in Kent, England.
-
D.
Luton Town Hall
Luton Town Hall is a prominent civic building and historic landmark in the center of Luton, England, serving as the town’s main municipal headquarters.
-
E.
Burnham Market
Burnham Market is a picturesque village in Norfolk, England, known for its Georgian architecture, boutique shops, and popularity as an upmarket holiday destination.
- 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.