Triple
T1095906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HRS high-resolution separator |
E24270
|
entity |
| Predicate | separationMethod |
P23060
|
FINISHED |
| Object | magnetic mass separation |
—
|
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: magnetic mass separation | Statement: [HRS high-resolution separator, separationMethod, magnetic mass separation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separationMethod Context triple: [HRS high-resolution separator, separationMethod, magnetic mass separation]
-
A.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
B.
separatedInto
Indicates that something has been divided or split into distinct parts, groups, or components.
-
C.
separationSchemaHoldsIn
Indicates that a particular separation or partitioning scheme is valid and correctly applies within a given context or situation.
-
D.
dividedBetween
Indicates that something is partitioned or shared among two or more distinct entities or groups.
-
E.
separationCentury
Indicates the century during which the separation or split between the related entities took place.
- F. None of above. chosen
Provenance (4 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_69a4940542308190ac2a0b1f730b7cfc |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b99ffb3481908cd168b6c58e1c6d |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b7448c148190a3c9a4158ebd05b4 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7da38888190a118ef20ce4ae9aa |
completed | March 1, 2026, 10:04 p.m. |
Created at: March 1, 2026, 7:42 p.m.