Triple
T4308252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenfield–Southend Line |
E94010
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Shenfield |
E302063
|
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: Shenfield | Statement: [Shenfield–Southend Line, connects, Shenfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shenfield Context triple: [Shenfield–Southend Line, connects, Shenfield]
-
A.
Shenfield
chosen
Shenfield is a suburban town in Essex, England, known as a key commuter hub with a major railway station connecting to London.
-
B.
Saffron Walden
Saffron Walden is a historic market town in Essex, England, known for its well-preserved medieval architecture and former saffron trade.
-
C.
Bocking
Bocking is a village and former civil parish that now forms part of the town of Braintree in Essex, England.
-
D.
Saxmundham
Saxmundham is a small market town in the English county of Suffolk, known as a local commercial and transport hub for the surrounding rural area.
-
E.
Ongar
Ongar is a small historic town and civil parish in the county of Essex in southeast England.
- 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_69b3451886588190a3dd1305ea7c58dc |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b350d2af088190ad7cb035d6e0f8c2 |
completed | March 12, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5db8e40f0819082a15006a1578405 |
completed | March 14, 2026, 10:05 p.m. |
Created at: March 12, 2026, 11:11 p.m.