Triple
T9128785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tribrachidium |
E219029
|
entity |
| Predicate | softTissue |
P6562
|
FINISHED |
| Object | lacked mineralized skeleton |
—
|
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: lacked mineralized skeleton | Statement: [Tribrachidium, softTissue, lacked mineralized skeleton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softTissue Context triple: [Tribrachidium, softTissue, lacked mineralized skeleton]
-
A.
isSoft
chosen
Indicates that one entity has a soft or yielding texture or consistency when touched or pressed.
-
B.
musculature
Indicates the relationship between an entity and the structure, development, or characteristics of its muscles.
-
C.
hasTissue
Indicates that one entity possesses, contains, or is associated with a specific tissue of another entity.
-
D.
fleshTexture
Indicates the tactile quality or surface feel of an entity’s flesh, such as how smooth, firm, soft, or coarse it is.
-
E.
skeleton
Indicates that one entity serves as the basic structural framework or underlying support for another.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8cc85b081908ee80db0e3b7df15 |
completed | April 1, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69cc6601d77881908299d58db6e64937 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:18 p.m.