Triple
T2718015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balaenidae |
E60012
|
entity |
| Predicate | buoyancyAdaptation |
P1964
|
FINISHED |
| Object | thick blubber layer |
—
|
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: thick blubber layer | Statement: [Balaenidae, buoyancyAdaptation, thick blubber layer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buoyancyAdaptation Context triple: [Balaenidae, buoyancyAdaptation, thick blubber layer]
-
A.
adaptationType
Indicates the specific kind or category of adaptation that relates one entity to another or to a particular context.
-
B.
adaptation
chosen
Indicates a relationship where one entity changes or is modified to better suit, function within, or correspond to another entity or context.
-
C.
baskingBehavior
Indicates engaging in a behavior of lying or resting in warmth or light, typically to absorb heat or comfort.
-
D.
displacementSubmerged
Indicates the amount of fluid displaced by an object when it is submerged.
-
E.
freelyFloating
Indicates that an entity is not fixed or attached to anything and can move or remain suspended without constraint in a surrounding medium.
- 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_69ab4b746d248190958e052045c09255 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdaad577c8190819d3c641c2406f4 |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8240920819087a812d816a55edb |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.