Triple
T31024909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | JP-4 |
E790542
|
entity |
| Predicate | energyContent |
P130232
|
FINISHED |
| Object | lower than JP-8 per unit volume |
—
|
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: lower than JP-8 per unit volume | Statement: [JP-4, energyContent, lower than JP-8 per unit volume]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: energyContent Context triple: [JP-4, energyContent, lower than JP-8 per unit volume]
-
A.
energyContribution
Indicates the amount or role of energy that one entity provides or contributes to another entity, process, or system.
-
B.
energyConcentration
Indicates a relationship where energy is gathered, focused, or accumulated within a specific region, object, or system.
-
C.
energyDensityByVolume
chosen
Indicates the amount of energy contained per unit of volume in a given system or material.
-
D.
energyPotential
Indicates a relationship where one entity possesses or confers the capacity to perform work or cause change (potential energy) relative to another entity or state.
-
E.
energyExpression
Indicates that one entity represents, encodes, or specifies the energy (or energy-related formula/value) associated with another entity or system.
- 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_69f224c811508190a7de096a5b1f5798 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 29, 2026, 8:58 p.m.