Triple
T14573683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Orwell |
E341982
|
entity |
| Predicate | flowsPast |
P4996
|
FINISHED |
| Object | Freston |
E328261
|
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: Freston | Statement: [River Orwell, flowsPast, Freston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Freston Context triple: [River Orwell, flowsPast, Freston]
-
A.
Freston
chosen
Freston is a small village in the English county of Suffolk, known for its rural setting near the River Orwell and historic Freston Tower.
-
B.
Greenford
Greenford is a suburban area in the London Borough of Ealing, known for its residential neighborhoods, parks, and transport links in West London.
-
C.
Cockfosters
Cockfosters is a suburban area in north London best known for its London Underground station that serves as the northern terminus of the Piccadilly line.
-
D.
Neasden
Neasden is a suburban area in northwest London, England, known for its residential character and proximity to major roads and rail links.
-
E.
Pyrford
Pyrford is a village in Surrey, England, known for its historic church, green spaces, and residential character near the town of Woking.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f49d58819094fcd2a702e146cb |
completed | April 14, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdf074410081909284345503eb3e9f |
completed | May 8, 2026, 2:17 p.m. |
Created at: April 10, 2026, 1:24 a.m.