Triple
T10845896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CE-20 |
E256007
|
entity |
| Predicate | oxidiser |
P7195
|
FINISHED |
| Object | liquid oxygen |
—
|
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: liquid oxygen | Statement: [CE-20, oxidiser, liquid oxygen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oxidiser Context triple: [CE-20, oxidiser, liquid oxygen]
-
A.
oxidizer
chosen
Indicates a relationship where one entity acts as an oxidizing agent that accepts electrons from, or promotes the oxidation of, another entity in a chemical process.
-
B.
oxidizerTank
Indicates that one entity functions as an oxidizer tank associated with, containing, or supplying oxidizer for another entity or system.
-
C.
oxidizerState
Indicates the physical or chemical state (e.g., solid, liquid, gas, concentration, or phase condition) in which an oxidizing agent exists during a reaction or process.
-
D.
laterOxidizer
Indicates that one oxidizer occurs or is applied after another in time within a given process or sequence.
-
E.
oxidizerTankMaterial
Indicates the material from which an oxidizer tank is constructed or composed.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d750d132e081909c977b3dc4110ca4 |
completed | April 9, 2026, 7:10 a.m. |
| PD | Predicate disambiguation | batch_69d70d2b51448190bae748ed6c23edde |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:19 p.m.