Triple
T26216544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | southern brown kiwi |
E655644
|
entity |
| Predicate | eggSizeRelativeToBody |
P86175
|
FINISHED |
| Object | very large |
—
|
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 | Statement: [southern brown kiwi, eggSizeRelativeToBody, very large]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eggSizeRelativeToBody Context triple: [southern brown kiwi, eggSizeRelativeToBody, very large]
-
A.
eggSizePattern
Indicates the characteristic pattern or distribution of sizes among a set of eggs.
-
B.
hasEggSize
chosen
Indicates that an entity possesses eggs characterized by a particular size or size category.
-
C.
eggMorphology
Indicates the relationship between an organism and the characteristics of its eggs, such as shape, size, structure, or surface features.
-
D.
eggType
Indicates the specific category or kind of egg associated with an entity (e.g., its classification or type).
-
E.
eggNumber
Indicates the specific count or identifier assigned to an individual egg within a set or sequence.
- 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_69ee5b4a77e08190bfcb5f8ecdc55abd |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60d1b90a88190a77dcad664786c53 |
completed | May 2, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69f5b007ec1c819092e2c3605933f60b |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:54 p.m.