Triple
T11408639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lowestoft Lighthouse |
E270305
|
entity |
| Predicate | markingFeature |
P99152
|
FINISHED |
| Object | UK’s most easterly point |
—
|
LITERAL 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: UK’s most easterly point | Statement: [Lowestoft Lighthouse, markingFeature, UK’s most easterly point]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: markingFeature Context triple: [Lowestoft Lighthouse, markingFeature, UK’s most easterly point]
-
A.
distinctiveMarking
Indicates that one entity bears a unique or distinguishing visual feature or pattern that sets it apart from others.
-
B.
namedFeature
Indicates that an entity has a specific feature or attribute that is explicitly given a name.
-
C.
markType
Indicates the specific category or kind of mark associated with or applied to an entity.
-
D.
metricalFeature
Indicates a relationship where one entity specifies or characterizes a metrical property or pattern of another entity.
-
E.
marque
Indicates that one entity is the brand or make associated with another entity, such as a product, vehicle, or manufactured item.
- F. None of above. chosen
Provenance (4 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8014e72748190a01bde2f0105cedb |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e70ffd708190b62a78ebcbce9f78 |
completed | April 9, 2026, 5:51 p.m. |
| PDg | Predicate description generation | batch_69d80010712c819089ea2e31e664abe1 |
completed | April 9, 2026, 7:37 p.m. |
Created at: April 8, 2026, 9:34 p.m.