Triple
T5382324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Denny |
E113115
|
entity |
| Predicate | hasNeighbour |
P5707
|
FINISHED |
| Object | Larbert |
E233250
|
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: Larbert | Statement: [Denny, hasNeighbour, Larbert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larbert Context triple: [Denny, hasNeighbour, Larbert]
-
A.
Larbert
chosen
Larbert is a small town in central Scotland, situated in the Falkirk council area and historically known for its industrial heritage and transport links.
-
B.
Galashiels
Galashiels is a town in the Scottish Borders known historically for its textile industry and as a regional commercial and educational hub.
-
C.
Lennoxtown
Lennoxtown is a small Scottish town situated at the foot of the Campsie Fells, historically associated with textile and chemical industries.
-
D.
Blantyre
Blantyre is a town in South Lanarkshire, Scotland, known historically for its association with explorer David Livingstone and its proximity to the city of Hamilton.
-
E.
Blantyre
Blantyre is Malawi’s largest commercial and industrial city, serving as a major economic and cultural hub in the country.
- 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_69bd4436a1988190af18dcff7fd306b4 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd86d163f88190939638d44fcb24a7 |
completed | March 20, 2026, 5:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8681d57c08190b72d1b010db3a065 |
completed | March 28, 2026, 11:45 p.m. |
Created at: March 20, 2026, 2:03 p.m.