Triple
T5766985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | COMPASS experiment |
E127238
|
entity |
| Predicate | usesTargetMaterial |
P24425
|
FINISHED |
| Object | NH3 |
—
|
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: NH3 | Statement: [COMPASS experiment, usesTargetMaterial, NH3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTargetMaterial Context triple: [COMPASS experiment, usesTargetMaterial, NH3]
-
A.
appliedToMaterial
chosen
Indicates that an action, process, or treatment is performed on or directed toward a specific material.
-
B.
usesTarget
Indicates that one entity employs, applies, or operates on another entity as its target or object of action.
-
C.
hasMaterialType
Indicates that something is composed of, made from, or characterized by a specific type of material.
-
D.
hasMaterialAspect
Indicates that something possesses a physical or tangible component or aspect as part of its overall nature or existence.
-
E.
usesTexture
Indicates that one entity employs or incorporates the texture of another entity in its appearance, design, or representation.
- 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_69c00834f6308190851b0abeddd8ed7e |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02acb12c081908e4beee4a957f9f9 |
completed | March 22, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69c021ce8d3c81909b332cb1c33a61ad |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:49 p.m.