Triple
T16494973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turritopsis dohrnii |
E400657
|
entity |
| Predicate | nematocystFunction |
P122225
|
FINISHED |
| Object | prey capture |
—
|
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: prey capture | Statement: [Turritopsis dohrnii, nematocystFunction, prey capture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nematocystFunction Context triple: [Turritopsis dohrnii, nematocystFunction, prey capture]
-
A.
hasCnidocytes
Indicates that an organism possesses cnidocytes, the specialized stinging cells characteristic of cnidarians.
-
B.
usesCnidaeFor
chosen
Indicates that an entity employs cnidae (stinging or adhesive organelles) as the means or mechanism for acting upon or interacting with another entity.
-
C.
hasTentacles
Indicates that an entity possesses tentacle-like appendages.
-
D.
venomDeliverySystem
Indicates the mechanism or method by which venom is produced, stored, and transferred from one organism to another.
-
E.
carnivoryType
Indicates the specific manner or strategy by which an organism engages in carnivory (i.e., how it feeds on animal prey).
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e3276b88190946a669b4d893a54 |
completed | April 18, 2026, 7:09 a.m. |
| PD | Predicate disambiguation | batch_69e296902d6c8190884ddb612b8c5b36 |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.