Triple
T7771974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sturnus |
E179093
|
entity |
| Predicate | feetType |
P12848
|
FINISHED |
| Object | perching feet adapted to passerines |
—
|
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: perching feet adapted to passerines | Statement: [Sturnus, feetType, perching feet adapted to passerines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feetType Context triple: [Sturnus, feetType, perching feet adapted to passerines]
-
A.
footType
chosen
Indicates the specific kind or classification of feet that an entity possesses or is characterized by.
-
B.
heightApproximateFeet
Indicates that one entity’s height is approximately equal to a specified value measured in feet.
-
C.
heightFeet
Indicates a relationship where a subject has its vertical size or stature specified in feet as a unit of measurement.
-
D.
depthFeetApprox
Indicates an approximate measurement of an entity’s depth expressed in feet.
-
E.
soleType
Indicates the specific kind or design category of a sole associated with an item (such as footwear or a similar object).
- 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_69c69f30602c819082ab52cd4af5c592 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c7045ebae88190a04c8f972795e615 |
completed | March 27, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69c7016f4ce881909c2e9f610255187b |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:11 p.m.