Triple
T29455152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blainville's beaked whale |
E747079
|
entity |
| Predicate | tailFlukes |
P63385
|
FINISHED |
| Object | broad flukes without a median notch or with only a slight notch |
—
|
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: broad flukes without a median notch or with only a slight notch | Statement: [Blainville's beaked whale, tailFlukes, broad flukes without a median notch or with only a slight notch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tailFlukes Context triple: [Blainville's beaked whale, tailFlukes, broad flukes without a median notch or with only a slight notch]
-
A.
hasTailFins
Indicates that an entity possesses tail fins as a physical feature or component.
-
B.
tailCharacteristic
chosen
Indicates that an entity possesses a particular property, feature, or quality specifically related to its tail.
-
C.
caudalFin
Indicates that an entity has or is associated with a caudal (tail) fin.
-
D.
hasFlippers
Indicates that an entity possesses flippers as a physical feature.
-
E.
tailBoom
Indicates that one entity serves as the tail boom (the rear structural extension supporting the tail assembly) of another entity, typically an aircraft or rotorcraft.
- 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_69f0a7a230488190b44a97fe3d16f731 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f66b6c26a481908018e663aee7b269 |
completed | May 2, 2026, 9:23 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:36 p.m.