Triple
T12285459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eubalaena |
E292816
|
entity |
| Predicate | lifeEnvironment |
P31092
|
FINISHED |
| Object | marine |
—
|
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: marine | Statement: [Eubalaena, lifeEnvironment, marine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lifeEnvironment Context triple: [Eubalaena, lifeEnvironment, marine]
-
A.
محیط زیست
Indicates a relationship involving the natural environment, such as the impact of actions on ecological systems, resources, and living conditions.
-
B.
environmentalFactor
Indicates that one entity functions as an environmental influence or condition that affects another entity or process.
-
C.
secondaryEnvironment
Indicates that an entity is associated with an additional or supporting environment distinct from its primary one.
-
D.
environmentSpecialization
Indicates that an entity is specifically adapted or tailored to operate within a particular environment or set of environmental conditions.
-
E.
environmentalMedium
chosen
Indicates the environmental context or medium (such as air, water, or soil) through which a substance, effect, or process occurs or is present.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9261e1570819084bb4fdb44aa6aea |
completed | April 10, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69d91c4d9a9c8190aeb7beaf9792d8f0 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.