Triple
T36204390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HIS |
E1047351
|
entity |
| Predicate | targetParticleType |
P3639
|
FINISHED |
| Object | heavy ions |
—
|
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: heavy ions | Statement: [HIS, targetParticleType, heavy ions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetParticleType Context triple: [HIS, targetParticleType, heavy ions]
-
A.
hasParticleType
chosen
Indicates that an entity is associated with, composed of, or characterized by a specific type or category of particle.
-
B.
usedParticle
Indicates that one entity employs or applies a particular particle (e.g., subatomic, linguistic, or material) in some process, context, or construction involving another entity.
-
C.
dominantParticleType
Indicates that one particle type is the primary or most prevalent component within a given system, context, or interaction.
-
D.
antiparticleType
Indicates that one particle is the corresponding antiparticle type of another particle.
-
E.
beamParticle
Indicates that one entity directs or projects another entity as a beam-like stream or focused flow.
- 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_69f76e414bdc8190996f15a544220a3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff0491409c8190be40f633a58da0b1 |
completed | May 9, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69ff040bb5cc81909534c7eee85d5e90 |
completed | May 9, 2026, 9:53 a.m. |
Created at: May 3, 2026, 4:08 p.m.