Triple
T17879067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | little spotted kiwi |
E447031
|
entity |
| Predicate | eggRelativeSize |
P86175
|
FINISHED |
| Object | very large relative to body size |
—
|
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: very large relative to body size | Statement: [little spotted kiwi, eggRelativeSize, very large relative to body size]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eggRelativeSize Context triple: [little spotted kiwi, eggRelativeSize, very large relative to body size]
-
A.
eggSizePattern
Indicates the characteristic pattern or distribution of sizes among a set of eggs.
-
B.
pyramidRelativeSize
Indicates how the size of one pyramid compares relative to another pyramid.
-
C.
hasEggSize
chosen
Indicates that an entity possesses eggs characterized by a particular size or size category.
-
D.
hasRelativeSize
Indicates that one entity’s size is being compared to another entity’s size, expressing a relative rather than absolute magnitude.
-
E.
relativeSizeOnTethys
Indicates how the size of one entity compares to another specifically in the context of Tethys.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0d219481909830fc269fc6beb5 |
completed | April 19, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:18 a.m.