Triple
T3917170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crewe Works |
E88869
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Crewe |
E45564
|
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: Crewe | Statement: [Crewe Works, locatedIn, Crewe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crewe Context triple: [Crewe Works, locatedIn, Crewe]
-
A.
Crewe
chosen
Crewe is a major railway town in Cheshire, England, historically known as a key junction on the British rail network and a center of railway engineering.
-
B.
Northwich
Northwich is a historic market and industrial town in Cheshire, England, traditionally known for its salt mining and chemical industries.
-
C.
Congleton
Congleton is a historic market town in the county of Cheshire in North West England, known for its industrial heritage and riverside setting.
-
D.
Telford
Telford is a given name most notably associated with Telford Taylor, the American lawyer and chief prosecutor at the Nuremberg Trials.
-
E.
Telford
Telford is a large new town in England’s West Midlands, known for its rapid post-war development and proximity to the Ironbridge Gorge World Heritage Site.
- 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_69aed955229881909e85e73ffab1d343 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeed5797508190adaddb84575d9bb3 |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b52864e0488190ab348a52cb9168b9 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:22 p.m.