Triple
T332935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish Sea |
E6662
|
entity |
| Predicate | hasMarineSpecies |
P12485
|
FINISHED |
| Object | harbour porpoise |
—
|
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: harbour porpoise | Statement: [Irish Sea, hasMarineSpecies, harbour porpoise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarineSpecies Context triple: [Irish Sea, hasMarineSpecies, harbour porpoise]
-
A.
hasOcean
Indicates that a geographic region, country, or landmass is bordered by or directly adjacent to a particular ocean.
-
B.
hasEndemicSpecies
Indicates that a place or region contains species that are native to and found only within that specific geographic area.
-
C.
hasNotableSea
Indicates that an entity is associated with or contains a sea that is considered notable or significant.
-
D.
hasInvasiveSpecies
Indicates that an area, ecosystem, or habitat contains one or more species that are non-native and causing or likely to cause ecological, economic, or environmental harm.
-
E.
hasOceanCoverage
Indicates that a specified area or region is covered by ocean to a certain extent or proportion.
- 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eac4d9d081908a624464e450fb0e |
completed | Feb. 28, 2026, 1:16 p.m. |
| PD | Predicate disambiguation | batch_69a2e94d99cc8190a112e4b630ec63c1 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea7d03a88190aab72e61d8673488 |
completed | Feb. 28, 2026, 1:15 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.