Triple
T25703898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brobdingnag |
E644535
|
entity |
| Predicate | scaleRelativeToGulliver |
P159189
|
FINISHED |
| Object | enormous |
—
|
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: enormous | Statement: [Brobdingnag, scaleRelativeToGulliver, enormous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scaleRelativeToGulliver Context triple: [Brobdingnag, scaleRelativeToGulliver, enormous]
-
A.
areaScale
Indicates a proportional relationship where one area value is a scaled (enlarged or reduced) version of another by a specific factor.
-
B.
scaleModelOf
Indicates that one entity is a scaled representation (larger or smaller but proportionally accurate) of another entity.
-
C.
sizeRelativeToPikmin
Indicates how the size of an entity compares to that of a Pikmin, typically expressing whether it is smaller, similar, or larger relative to a Pikmin.
-
D.
magnitudeScale
Indicates the scale or measurement system used to quantify the magnitude or intensity of something.
-
E.
scaleCharacteristic
Indicates that one entity specifies or describes a measurable property or dimension (such as size, magnitude, or extent) used as the scale for evaluating or comparing another entity.
- F. None of above. chosen
Provenance (4 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_69e77e83c8ec8190bf52fcdac4838984 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fc0f911c819083ea7748550df1d0 |
completed | May 2, 2026, 1:28 p.m. |
| PD | Predicate disambiguation | batch_69f4938262ac8190b41f922d0407d272 |
completed | May 1, 2026, 11:50 a.m. |
| PDg | Predicate description generation | batch_69f497b8abb88190bb672cf6907c4b8d |
completed | May 1, 2026, 12:08 p.m. |
Created at: April 21, 2026, 9 p.m.