Triple
T23722320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulf of Morbihan |
E586176
|
entity |
| Predicate | hasNumberOfIslandsApprox |
P83748
|
FINISHED |
| Object | about 40 |
—
|
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: about 40 | Statement: [Gulf of Morbihan, hasNumberOfIslandsApprox, about 40]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfIslandsApprox Context triple: [Gulf of Morbihan, hasNumberOfIslandsApprox, about 40]
-
A.
hasApproximateIslandsCount
Indicates that an entity is associated with an estimated or non-exact number of islands.
-
B.
approximateNumberOfIslands
chosen
Indicates an estimated or rough count of how many islands are present or associated with a given context.
-
C.
hasNumberOfMajorIslands
Indicates the quantitative relationship specifying how many major islands are associated with a given entity.
-
D.
hasIslandAreaApprox
Indicates that an island’s area is approximately equal to a specified value or falls within an approximate range.
-
E.
hasNumberOfInhabitedIslands
Indicates the relationship that specifies how many islands within a given area or jurisdiction are inhabited.
- F. None of above.
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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b912a7548190afcfa03dd9adc47e |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:04 p.m.