Triple
T15460399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Compsognathus |
E371882
|
entity |
| Predicate | hindlimbFeature |
P26649
|
FINISHED |
| Object | long hind legs adapted for running |
—
|
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: long hind legs adapted for running | Statement: [Compsognathus, hindlimbFeature, long hind legs adapted for running]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hindlimbFeature Context triple: [Compsognathus, hindlimbFeature, long hind legs adapted for running]
-
A.
limbMorphology
chosen
Indicates the structural form, shape, and configuration of an organism’s limbs in relation to its body.
-
B.
limbType
Indicates the specific kind or category of limb associated with an entity (e.g., arm, leg, wing, fin).
-
C.
hasHindLegsOf
Indicates that one entity possesses or is characterized by the hind legs belonging to or derived from another entity.
-
D.
forelimbFunction
Indicates the functional role or use of an entity’s forelimbs in performing actions or behaviors.
-
E.
hasForelimbs
Indicates that an entity possesses front limbs or appendages used for movement, manipulation, or support.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f17663c8190b995c7c3129c90d6 |
completed | April 16, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69ded284bd008190b31c53b4f1cebadd |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:32 a.m.