Triple
T3035841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic puffin |
E83005
|
entity |
| Predicate | foragingMethod |
P10557
|
FINISHED |
| Object | pursuit diving |
—
|
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: pursuit diving | Statement: [Atlantic puffin, foragingMethod, pursuit diving]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foragingMethod Context triple: [Atlantic puffin, foragingMethod, pursuit diving]
-
A.
foragingStrategy
chosen
Indicates the method or pattern an organism uses to search for, obtain, and exploit food resources.
-
B.
foragingStratum
Indicates the vertical layer or height within a habitat where an organism typically searches for and obtains its food.
-
C.
foodSources
Indicates a relationship where one entity serves as a source of food or nourishment for another entity.
-
D.
preyCaptureMechanism
Indicates the method or strategy an organism uses to locate, seize, and secure its prey.
-
E.
traditionalSubsistence
Indicates that an entity relies on customary, small-scale methods of obtaining food and resources (such as hunting, gathering, fishing, or small-scale farming) primarily for direct consumption rather than for market sale.
- 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_69ad8b2298908190a7cb4e9bdbf064d0 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b2bb60c8190b1721f832f2581a1 |
completed | March 8, 2026, 3:52 p.m. |
| PD | Predicate disambiguation | batch_69ad961e2a408190afb1759132701305 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.