Triple
T28038658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P-body |
E708477
|
entity |
| Predicate | hasHeightRelativeToAtlas |
P161096
|
FINISHED |
| Object | taller |
—
|
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: taller | Statement: [P-body, hasHeightRelativeToAtlas, taller]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeightRelativeToAtlas Context triple: [P-body, hasHeightRelativeToAtlas, taller]
-
A.
hasHeight
Indicates that one entity possesses a specific vertical measurement or stature.
-
B.
hasScaleHeight
Indicates the characteristic vertical distance over which a quantity (such as pressure, density, or concentration) decreases by a fixed factor in a stratified medium.
-
C.
hasRelativeSize
Indicates that one entity’s size is being compared to another entity’s size, expressing a relative rather than absolute magnitude.
-
D.
heightRelation
chosen
Indicates a comparative relationship between entities based on their heights, such as one being taller, shorter, or the same height as another.
-
E.
portrayedByCharacterHeightRelative
Indicates that one character’s height is depicted or described in relation to another character’s height.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f707f7959881908f037f0d6b1d0c36 |
completed | May 3, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69f700fc274c8190a128593dc7c7abd0 |
completed | May 3, 2026, 8:02 a.m. |
Created at: April 27, 2026, 8:23 p.m.