Triple
T25828814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Planck density |
E650603
|
entity |
| Predicate | isExtremelyHighComparedTo |
P13790
|
FINISHED |
| Object | nuclear density |
—
|
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: nuclear density | Statement: [Planck density, isExtremelyHighComparedTo, nuclear density]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isExtremelyHighComparedTo Context triple: [Planck density, isExtremelyHighComparedTo, nuclear density]
-
A.
hasHigh
Indicates that an entity possesses a high level, degree, or intensity of a specified attribute or property.
-
B.
isHigherThan
chosen
Indicates that one entity has a greater value, level, or position than another entity.
-
C.
hasHighPerUnitValueAgainst
Indicates that one entity yields a relatively high value or benefit per unit when used against or applied to another entity.
-
D.
isElevatedAbove
Indicates that one entity is positioned at a higher vertical level or altitude than another entity.
-
E.
hasHighDensityOf
Indicates that one entity contains or exhibits a large concentration or amount of another entity within a given area, volume, or context.
- 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_69e7ab37438081908f1ccf6284839520 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6019807f08190bbeb8be744551fdf |
completed | May 2, 2026, 1:52 p.m. |
| PD | Predicate disambiguation | batch_69f4938b960081909b53c074a3e0c7c2 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 7:37 a.m.