Triple
T23108645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gresford |
E576249
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Marford |
E814593
|
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: Marford | Statement: [Gresford, hasNearbySettlement, Marford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marford Context triple: [Gresford, hasNearbySettlement, Marford]
-
A.
Marford
chosen
Marford is a village in Wrexham County Borough, Wales, known for its distinctive Gothic-style architecture and historic character.
-
B.
Fairville
Fairville is a residential neighbourhood located on the west side of Saint John, New Brunswick, Canada.
-
C.
Nutwood
Nutwood is the idyllic English village that serves as the primary setting for the classic British children's comic strip and stories about Rupert Bear.
-
D.
Nordhoff
Nordhoff is a surname most notably associated with American author and journalist Charles Nordhoff.
-
E.
Westmore
Westmore is a surname most prominently associated with a renowned Hollywood family of makeup artists who helped define cinematic makeup in the 20th century.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0d3d4881908e32837b3fbbb406 |
completed | April 29, 2026, 4:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c23e7fdec8190a7ac3e8f18e677d8 |
completed | May 19, 2026, 8:48 a.m. |
Created at: April 17, 2026, 3:58 p.m.