Triple
T17029580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clough, County Down |
E413155
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Seaforde |
E1184456
|
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: Seaforde | Statement: [Clough, County Down, near, Seaforde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seaforde Context triple: [Clough, County Down, near, Seaforde]
-
A.
Seaforde
chosen
Seaforde is a small village in County Down, Northern Ireland, known for its historic demesne and ornamental gardens.
-
B.
Seaford House
Seaford House is a historic London mansion on Belgrave Square, notable for its grand architecture and use as a government and military educational institution.
-
C.
Marsh Hall
Marsh Hall is a historic academic building on Yale University's Prospect Hill campus, used for university offices and research facilities.
-
D.
Kingsmill
Kingsmill is a small locality in County Armagh, Northern Ireland, historically known for the 1976 Kingsmill massacre during the Troubles.
-
E.
Netherwood
Netherwood is a New Jersey Transit commuter rail station serving the Netherwood neighborhood of Plainfield, New Jersey.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d858448190acfe81f10d83ed4b |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b553c588190b46785b85142dce5 |
completed | May 10, 2026, 11:57 p.m. |
Created at: April 10, 2026, 5:33 a.m.