Triple
T6666025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barton Broad |
E151604
|
entity |
| Predicate | relativeSizeInNorfolkBroads |
P72330
|
FINISHED |
| Object | one of the largest broads |
—
|
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: one of the largest broads | Statement: [Barton Broad, relativeSizeInNorfolkBroads, one of the largest broads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeSizeInNorfolkBroads Context triple: [Barton Broad, relativeSizeInNorfolkBroads, one of the largest broads]
-
A.
relativeSizeInArchipelago
Indicates the comparative size relationship of an entity relative to other entities within the same archipelago.
-
B.
islandSize
Indicates the size or area measurement associated with a particular island.
-
C.
southernShore
Indicates that one entity is located along or forms the southern shoreline or coastal edge of another entity.
-
D.
distanceToHunstanton
Indicates the measured spatial distance between a given entity and the location Hunstanton.
-
E.
areaScale
Indicates a proportional relationship where one area value is a scaled (enlarged or reduced) version of another by a specific factor.
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
| PDg | Predicate description generation | batch_69c6ce72809c8190be85f6e42ca1c8ea |
completed | March 27, 2026, 6:37 p.m. |
Created at: March 27, 2026, 2:02 p.m.