Triple
T36934383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NMR spectroscopy |
E913571
|
entity |
| Predicate | hasInstrumentComponent |
P202890
|
FINISHED |
| Object | superconducting magnet |
—
|
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: superconducting magnet | Statement: [NMR spectroscopy, hasInstrumentComponent, superconducting magnet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInstrumentComponent Context triple: [NMR spectroscopy, hasInstrumentComponent, superconducting magnet]
-
A.
hasInstrumentClass
Indicates that an action or process is carried out using an instrument that belongs to a specified class or category of instruments.
-
B.
hasInstrumentRole
Indicates that an entity participates in an action or process specifically in the capacity of an instrument or means by which that action is carried out.
-
C.
isInstrumentFor
Indicates that something is used as a tool or means to perform a particular action or achieve a specific outcome.
-
D.
hasInstrumentNamedAfter
Indicates that an entity has an instrument that is named in honor of, or derived from the name of, another entity.
-
E.
usesInstrument
Indicates that an agent performs an action by employing a specific instrument or tool as the means to carry it out.
- 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_69f76e896c988190880c130e01303dd4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00cbae75988190974f5b45a2e62326 |
completed | May 10, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_6a00cabe4c5881909cca5efbe494e0d1 |
completed | May 10, 2026, 6:13 p.m. |
| PDg | Predicate description generation | batch_6a00cbad83e88190ba792d3172370f63 |
completed | May 10, 2026, 6:17 p.m. |
Created at: May 3, 2026, 4:13 p.m.