Triple
T22412857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GK Persei |
E554034
|
entity |
| Predicate | ejectedMaterial |
P49676
|
FINISHED |
| Object | expanding knots and filaments |
—
|
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: expanding knots and filaments | Statement: [GK Persei, ejectedMaterial, expanding knots and filaments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ejectedMaterial Context triple: [GK Persei, ejectedMaterial, expanding knots and filaments]
-
A.
involvesParticleEjection
Indicates that the action or process includes the emission or release of particles from a source.
-
B.
typicalEjectedMass
Indicates the characteristic amount of mass that is usually expelled from a system or object during an ejection event.
-
C.
hasEjecta
chosen
Indicates that one entity produces or is associated with material expelled or thrown out from another entity as a result of an energetic event or process.
-
D.
ejectorType
Indicates the specific kind or category of ejector mechanism associated with an entity or system.
-
E.
ejection
Indicates the forceful expulsion or removal of one entity from another entity, system, or location.
- 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_69e11e4e6ce8819085a1e06d886bf21c |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1594496348190ba25dc0193d092f2 |
completed | April 29, 2026, 1:05 a.m. |
| PD | Predicate disambiguation | batch_69e8989495bc81909d2699fce5992e28 |
completed | April 22, 2026, 9:44 a.m. |
Created at: April 16, 2026, 8:46 p.m.