Triple
T36703279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skiffia francesae |
E906287
|
entity |
| Predicate | hasFertilization |
P16675
|
FINISHED |
| Object | internal fertilization |
—
|
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: internal fertilization | Statement: [Skiffia francesae, hasFertilization, internal fertilization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFertilization Context triple: [Skiffia francesae, hasFertilization, internal fertilization]
-
A.
hasFertility
Indicates that one entity possesses or exhibits the capacity to reproduce or generate offspring.
-
B.
fertilizationRequires
Indicates that a fertilization event can only occur if a specified condition, resource, or process is present or has taken place.
-
C.
fertilizationType
chosen
Indicates the method or process by which fertilization occurs or is achieved between reproductive cells.
-
D.
fertilityStatus
Indicates the reproductive condition or capability of an entity, such as whether it is fertile, infertile, or at a particular stage of fertility.
-
E.
hasHatch
Indicates that one entity possesses or is equipped with a hatch, such as an opening or access panel.
- 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_69f76e7195c48190b5580c9cfb01e95f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.