Triple
T17315276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Blowhole |
E420406
|
entity |
| Predicate | relativeSizeComparedTo |
P23282
|
FINISHED |
| Object | smaller than Kiama Blowhole |
—
|
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: smaller than Kiama Blowhole | Statement: [Little Blowhole, relativeSizeComparedTo, smaller than Kiama Blowhole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeSizeComparedTo Context triple: [Little Blowhole, relativeSizeComparedTo, smaller than Kiama Blowhole]
-
A.
scaleComparison
chosen
Indicates a relationship where two or more entities are compared in terms of their size, magnitude, or scale relative to one another.
-
B.
relativeSizeOnTethys
Indicates how the size of one entity compares to another specifically in the context of Tethys.
-
C.
relativeSizeWithinSite
Indicates the comparative size relationship of one entity to another within the same site or local context.
-
D.
relativeFruitSize
Indicates the comparative size relationship between one fruit and another (e.g., larger than, smaller than, or similar in size).
-
E.
relativeLength
Indicates a comparative relationship between entities based on how long they are relative to one 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4399c6ad88190ba7fcf1d2d53171c |
completed | April 19, 2026, 2:10 a.m. |
| PD | Predicate disambiguation | batch_69e3b01b9d1c8190a406dd941c9b11a1 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:43 a.m.