Triple
T14725210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ceremonial county of Gloucestershire |
E345921
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Lydney |
E72705
|
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: Lydney | Statement: [Ceremonial county of Gloucestershire, containsSettlement, Lydney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lydney Context triple: [Ceremonial county of Gloucestershire, containsSettlement, Lydney]
-
A.
Lydney
chosen
Lydney is a small town in southwest England situated on the River Severn near the Forest of Dean.
-
B.
Lynndyl
Lynndyl is a small rural town located in central Utah in the western United States.
-
C.
Langden
Langden is an alternative spelling variant of the name Langdon, typically used as a surname or place name.
-
D.
Ashton Vale
Ashton Vale is a residential and industrial suburb on the southwestern edge of Bristol, England.
-
E.
Slindon
Slindon is a historic village in West Sussex, England, known for its traditional architecture, surrounding woodland, and association with the National Trust.
- 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_69d822e5911c8190ba589f957dbd9ba7 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec25e9a14819081fa06fc601f295d |
completed | April 14, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72a181708190816c391f6a5d06f0 |
completed | May 8, 2026, 11:32 p.m. |
Created at: April 10, 2026, 1:29 a.m.