Triple
T2369091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Zealand fur seal |
E46047
|
entity |
| Predicate | swimmingAbility |
P19130
|
FINISHED |
| Object | agile swimmer |
—
|
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: agile swimmer | Statement: [New Zealand fur seal, swimmingAbility, agile swimmer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: swimmingAbility Context triple: [New Zealand fur seal, swimmingAbility, agile swimmer]
-
A.
swimmingLevel
chosen
Indicates the degree of proficiency or skill an entity has in swimming.
-
B.
canSwim
Indicates that an entity has the ability to move through water by swimming.
-
C.
swimmingType
Indicates the manner or style in which an entity performs the action of swimming.
-
D.
hasWaterActivity
Indicates that one entity possesses, exhibits, or is characterized by a particular level or type of water-related activity (such as moisture content, water availability, or water-based processes).
-
E.
hasLifeguardService
Indicates that a location or facility provides lifeguard supervision or rescue services.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc76dcaa481908567a068bd61e5ad |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.